Francesca Toni

AAMAS Conference 2026 Conference Paper

ArgLLM-App: An Interactive System for Argumentative Reasoning with Large Language Models

• Adam Dejl
• Deniz Gorur
• Francesca Toni

Argumentative LLMs (ArgLLMs) are an existing approach leveraging Large Language Models (LLMs) and computational argumentation for decision-making, with the aim of making the resulting decisions faithfully explainable to and contestable by humans. Here weproposeaweb-basedsystemimplementingArgLLM-empowered agents for binary tasks. ArgLLM-App supports visualisation of the produced explanations and interaction with human users, allowing themtoidentifyandcontestanymistakesinthesystem’sreasoning. It is highly modular and enables drawing information from trusted external sources. ArgLLM-App is publicly available at argllm. app, with a video demonstration at youtu. be/vzwlGOr0sPM.

AAAI Conference 2026 Conference Paper

Argumentative Debates for Transparent Bias Detection

• Hamed Ayoobi
• Nico Potyka
• Anna Rapberger
• Francesca Toni

As the use of AI in society grows, addressing emerging biases is essential to prevent systematic discrimination. Several bias detection methods have been proposed, but, with few exceptions, these tend to ignore transparency. Instead, interpretability and explainability are core requirements for algorithmic fairness, even more so than for other algorithmic solutions, given the human-oriented nature of fairness. We present ABIDE (Argumentative BIas detection by DEbate), a novel framework that structures bias detection transparently as debate, guided by an underlying argument graph as understood in (formal and computational) argumentation. The arguments are about the success chances of groups in local neighbourhoods and the significance of these neighbourhoods. We evaluate ABIDE experimentally and demonstrate its strengths in performance against an argumentative baseline.

AAMAS Conference 2026 Conference Paper

Argumentative Human-AI Decision-Making: Toward AI Agents That Reason With Us, Not For Us

• Stylianos Loukas Vasileiou
• Antonio Rago
• Francesca Toni
• William Yeoh

Computational argumentation offers formal frameworks for transparent, verifiable reasoning but has traditionally been limited by its reliance on domain-specific information and extensive feature engineering. In contrast, LLMs excel at processing unstructured text, yet their opaque nature makes their reasoning difficult to evaluate and trust. We argue that the convergence of these fields will lay the foundation for a new paradigm: Argumentative Human-AI Decision-Making. We analyze how the synergy of argumentation framework mining, argumentation framework synthesis, and argumentative reasoning enables agents that do not just justify decisions, but engage in dialectical processes where decisions are contestable and revisable – reasoning with humans rather than for them. This convergence of computational argumentation and LLMs is essential for human-aware, trustworthy AI in high-stakes domains.

AAMAS Conference 2026 Conference Paper

Constrained Assumption-Based Argumentation Frameworks

• Emanuele De Angelis
• Fabio Fioravanti
• Maria Chiara Meo
• Alberto Pettorossi
• Maurizio Proietti
• Francesca Toni

Assumption-based Argumentation (ABA) is a well-established form of structured argumentation. ABA frameworks with an underlying atomic language are widely studied, but their applicability is limited by a representational restriction to ground (variable-free) arguments and attacks built from propositional atoms. In this paper, we lift this restriction and propose a novel notion of constrained ABA (CABA), whose components, as well as arguments built from them, may include constrained variables, ranging over possibly infinite domains. We define non-ground semantics for CABA, in terms of various notions of non-ground attacks. We show that the new semantics conservatively generalise standard ABA semantics.

AAMAS Conference 2026 Conference Paper

From User Preferences to Base Score Extraction Functions in Gradual Argumentation

• Aniol Civit
• Antonio Rago
• Antonio Andriella
• Guillem Alenyà
• Francesca Toni

Gradual argumentation is a sub-field of Computational Argumentation from symbolic AI which is attracting attention for its ability to support transparent and contestable AI systems. It is considered a useful tool in domains such as decision-making, recommendation, debate analysis, amongst others. The outcomes in such domains are usually dependent on the arguments’ base scores, which must be selected carefully. Often, this selection process requires user expertise and may not always be straightforward. On the other hand, organising the arguments by preference could simplify the task. In this work, we introduce Base Score Extraction Functions, which provide a mapping from users’ preferences over arguments to base scores. These functions can be applied to the arguments of a Bipolar Argumentation Framework (BAF), supplemented with preferences, to obtain a Quantitative Bipolar Argumentation Framework (QBAF), allowing the use of well-established computational tools in gradual argumentation. We outline the desirable properties of Base Score Extraction Functions, discuss some design choices, and provide an algorithm for base score extraction. Our method incorporates an approximation of non-linearities in human preferences to allow for better approximation of the real ones. Finally, we evaluate our approach both theoretically and experimentally in a robotics setting, and offer recommendations for selecting appropriate gradual semantics in practice.

AAAI Conference 2026 Conference Paper

Heterogeneous Graph Neural Networks for Assumption-Based Argumentation

• Preesha Gehlot
• Anna Rapberger
• Fabrizio Russo
• Francesca Toni

Assumption‐Based Argumentation (ABA) is a powerful structured argumentation formalism, but exact computation of extensions under stable semantics is intractable for large frameworks. We present the first Graph Neural Network (GNN) approach to approximate credulous acceptance in ABA. To leverage GNNs, we model ABA frameworks via a dependency graph representation encoding assumptions, claims and rules as nodes, with heterogeneous edge labels distinguishing support, derive and attack relations. We propose two GNN architectures—ABAGCN and ABAGAT—that stack residual heterogeneous convolution or attention layers, respectively, to learn node embeddings. Our models are trained on the ICCMA 2023 benchmark, augmented with synthetic ABAFs, with hyperparameters optimised via Bayesian search. Empirically, both ABAGCN and ABAGAT outperform a state‐of‐the‐art GNN baseline that we adapt from the abstract argumentation iterature, achieving a node‐level F1 score of up to 0.71 on the ICCMA instances. Finally, we develop a sound polynomial time extension‐reconstruction algorithm driven by our predictor: it reconstructs stable extensions with F1 above 0.85 on small ABAFs and maintains an F1 of about 0.58 on large frameworks. Our work opens new avenues for scalable approximate reasoning in structured argumentation.

AAMAS Conference 2026 Conference Paper

Retrieval- and Argumentation-Enhanced Multi-Agent LLMs for Judgmental Forecasting

• Deniz Gorur
• Antonio Rago
• Francesca Toni

Judgmental forecasting is the task of making predictions about future events based on human judgment. This task can be seen as a form of claim verification, where the claim corresponds to a future event and the task is to assess the plausibility of that event. In this paper, we propose a novel multi-agent framework for claim verification, whereby different agents may disagree on claim veracity and bring specific evidence for and against the claims, represented as quantitative bipolar argumentation frameworks (QBAFs). We then instantiate the framework with a variety of agents realised with Large Language Models (LLMs): (1) ArgLLM agents, an existing approachforclaimverificationthatgeneratesandevaluatesQBAFs; (2) RbAM agents, whereby LLM-empowered Relation-based Argument Mining (RbAM) from external sources is used to generate QBAFs; (3) RAG-ArgLLM agents, extending ArgLLM agents with a form of Retrieval-Augmented Generation (RAG) of arguments from external sources. Finally, we conduct experiments with two standard judgmental forecasting datasets, with instances of our framework with two or three agents, empowered by six different base LLMs. We observe that combining evidence from agents can improve forecasting accuracy, especially in the case of three agents, while providing an explainable combination of evidence.

AAMAS Conference 2026 Conference Paper

Strength Change Explanations in Quantitative Argumentation

• Timotheus Kampik
• Xiang Yin
• Nico Potyka
• Francesca Toni

In order to make argumentation-based inference contestable, it is crucial to explain what changes can achieve a desired (instead of the contested) inference result. To this end, we introduce strength change explanations for quantitative (bipolar) argumentation graphs. Strength change explanations describe changes to the initial strengths of a subset of the arguments in a given graph that can achieve a desired ordering based on the final strengths of some (potentially different) subset of arguments. We show that the existing notions of inverse and counterfactual problems can be reduced to strength change explanations. We also prove basic soundness and completeness properties of our strength change explanations, and demonstrate their existence and non-existence in some special cases. By applying a heuristic search, we demonstrate that we can often successfully find strength change explanations for layered graphs that are common in typical application scenarios; still, limitations remain for settings where we do not provide guarantees for the presence (or absence) of explanations.

KR Conference 2025 Conference Paper

A Methodology for Incompleteness-Tolerant and Modular Gradual Semantics for Argumentative Statement Graphs

• Antonio Rago
• Stylianos Loukas Vasileiou
• Son Tran
• Francesca Toni
• William Yeoh

Gradual semantics (GS) have demonstrated great potential in argumentation, in particular for deploying quantitative bipolar argumentation frameworks (QBAFs) in a number of real-world settings, from judgmental forecasting to explainable AI. In this paper, we provide a novel methodology for obtaining GS for statement graphs, a form of structured argumentation framework, where arguments and relations between them are built from logical statements. Our methodology differs from existing approaches in the literature in two main ways. First, it naturally accommodates incomplete information, so that arguments with partially specified premises can play a meaningful role in the evaluation. Second, it is modularly defined to leverage on any GS for QBAFs. We also define a set of novel properties for our GS and study their suitability alongside a set of existing properties (adapted to our setting) for two instantiations of our GS, demonstrating their advantages over existing approaches.

ECAI Conference 2025 Conference Paper

ADA-X: An Online System for Fully Automated, Explainable Review Aggregation

• Lingjun Gao
• Hafizh Muyassar
• Yeva Hunanyan
• Shane Pongpanich
• Antonio Rago 0001
• Francesca Toni

Today’s online platforms, e. g. in e-commerce, often offer users numerous competing options in single product categories, e. g. televisions or watches, making it difficult for the users to identify the best option to suit their preferences. To ease this process, many platforms provide users with simple scores resulting from the aggregation of other users’ reviews. However, these scoring systems may oversimplify the underlying information and lack explanatory context. Our main contribution in this demonstration paper is a novel online system for aggregating customer reviews and explaining the aggregation to users. The system operates through a multi-stage pipeline: it first applies novel automatic ontology extraction methods using BERT or Large Language Models to identify key aspects from customer reviews, then constructs support and attack relations between these aspects using Argumentative Dialogical Agents (ADAs), an existing methodology for generating argumentative analyses of aspects. Finally, it generates ontology-driven, explainable aggregations of the reviews. We evaluate the performance of our system (which we call ADA-X) on the Amazon and Disneyland review datasets, focusing the ontology quality using the LLM-as-a-judge method and aggregation performance against the original Amazon and Disneyland ratings. The demonstration is available at https: //ada-x. co. uk/.

ECAI Conference 2025 Conference Paper

Argumentation for Explainable Workforce Optimisation

• Jennifer Leigh
• Dimitrios Letsios
• Alessandro Mella
• Lucio Machetti
• Francesca Toni

Workforce management is a complex problem involving the optimisation of the makespan and travel distance required for a team of operators to complete a set of jobs, using a set of instruments. A crucial challenge in workforce management is accommodating changes at execution time so that explanations are provided to all stakeholders involved. Here, we show that, by understanding workforce management as abstract argumentation in an industrial application, we can accommodate change and obtain faithful explanations. We show, with a user study, that our tool and explanations lead to faster and more accurate problem solving than conventional manual approaches.

AAAI Conference 2025 Conference Paper

Argumentative Large Language Models for Explainable and Contestable Claim Verification

• Gabriel Freedman
• Adam Dejl
• Deniz Gorur
• Xiang Yin
• Antonio Rago
• Francesca Toni

The profusion of knowledge encoded in large language models (LLMs) and their ability to apply this knowledge zero-shot in a range of settings makes them promising candidates for use in decision-making. However, they are currently limited by their inability to provide outputs which can be faithfully explained and effectively contested to correct mistakes. In this paper, we attempt to reconcile these strengths and weaknesses by introducing argumentative LLMs (ArgLLMs), a method for augmenting LLMs with argumentative reasoning. Concretely, ArgLLMs construct argumentation frameworks, which then serve as the basis for formal reasoning in support of decision-making. The interpretable nature of these argumentation frameworks and formal reasoning means that any decision made by ArgLLMs may be explained and contested. We evaluate ArgLLMs’ performance experimentally in comparison with state-of-the-art techniques, in the context of the decision-making task of claim verification. We also define novel properties to characterise contestability and assess ArgLLMs formally in terms of these properties.

AIJ Journal 2025 Journal Article

Argumentative review aggregation and dialogical explanations

• Antonio Rago
• Oana Cocarascu
• Joel Oksanen
• Francesca Toni

The aggregation of online reviews is one of the dominant methods of quality control for users in various domains, from retail to entertainment. Consequently, explainable aggregation of reviews is increasingly sought-after. We introduce quantitative argumentation technology to this setting, towards automatically generating reasoned review aggregations equipped with dialogical explanations. To this end, we define a novel form of argumentative dialogical agent (ADA), using ontologies to harbour information from reviews into argumentation frameworks. These agents may then be evaluated with a quantitative argumentation semantics and used to mediate the generation of dialogical explanations for item recommendations based on the reviews. We show how to deploy ADAs in three different contexts in which argumentation frameworks are mined from text, guided by ontologies. First, for hotel recommendations, we use a human-authored ontology and exemplify the potential range of dialogical explanations afforded by ADAs. Second, for movie recommendations, we empirically evaluate an ADA based on a bespoke ontology (extracted semi-automatically, by natural language processing), by demonstrating that its quantitative evaluations, which are shown to satisfy desirable theoretical properties, are comparable with those on a well-known movie review aggregation website. Finally, for product recommendation in e-commerce, we use another bespoke ontology (extracted fully automatically, by natural language processing, from a website's reviews) to construct an ADA which is then empirically evaluated favourably against review aggregations from the website.

ECAI Conference 2025 Conference Paper

Argumentatively Coherent Judgmental Forecasting

• Deniz Gorur
• Antonio Rago 0001
• Francesca Toni

Judgmental forecasting employs human opinions to make predictions about future events, rather than exclusively historical data as in quantitative forecasting. When these opinions form an argumentative structure around forecasts, it is useful to study the properties of the forecasts from an argumentative perspective. In this paper, we advocate and formally define a property of argumentative coherence, which, in essence, requires that a forecaster’s reasoning is coherent with their forecast. We then conduct three evaluations with our notion of coherence. First, we assess the impact of enforcing coherence on human forecasters as well as on Large Language Model (LLM)-based forecasters, given that they have recently shown to be competitive with human forecasters. In both cases, we show that filtering out incoherent predictions improves forecasting accuracy consistently, supporting the practical value of coherence in both human and LLM-based forecasting. Then, via crowd-sourced user experiments, we show that, despite its apparent intuitiveness and usefulness, users do not generally align with this coherence property. This points to the need to integrate, within argumentation-based judgmental forecasting, mechanisms to filter out incoherent opinions before obtaining group forecasting predictions.

IJCAI Conference 2025 Conference Paper

Counterfactual Explanations Under Model Multiplicity and Their Use in Computational Argumentation

• Gianvincenzo Alfano
• Adam Gould
• Francesco Leofante
• Antonio Rago
• Francesca Toni

Counterfactual explanations (CXs) are widely recognised as an essential technique for providing recourse recommendations for AI models. However, it is not obvious how to determine CXs in model multiplicity scenarios, where equally performing but different models can be obtained for the same task. In this paper, we propose novel qualitative and quantitative definitions of CXs based on explicit, nested quantification over (groups) of model decisions. We also study properties of these notions and identify decision problems of interest therefor. While our CXs are broadly applicable, in this paper we instantiate them within computational argumentation where model multiplicity naturally emerges, e. g. with incomplete and case-based argumentation frameworks. We then illustrate the suitability of our CXs for model multiplicity in legal and healthcare contexts, before analysing the complexity of the associated decision problems.

ECAI Conference 2025 Conference Paper

Explainable Prediction of the Mechanical Properties of Composites with CNNs

• Varun Raaghav
• Dimitrios Bikos
• Antonio Rago 0001
• Francesca Toni
• Maria Charalambides

Composites are amongst the most important materials manufactured today, as evidenced by their use in countless applications. In order to establish the suitability of composites in specific applications, finite element (FE) modelling, a numerical method based on partial differential equations, is the industry standard for assessing their mechanical properties. However, FE modelling is exceptionally costly from a computational viewpoint, a limitation which has led to efforts towards applying AI models to this task. However, in these approaches: the chosen model architectures were rudimentary, feed-forward neural networks giving limited accuracy; the studies focused on predicting elastic mechanical properties, without considering material strength limits; and the models lacked transparency, hindering trustworthiness by users. In this paper, we show that convolutional neural networks (CNNs) equipped with methods from explainable AI (XAI) can be successfully deployed to solve this problem. Our approach uses customised CNNs trained on a dataset we generate using transverse tension tests in FE modelling to predict composites’ mechanical properties, i. e. , Young’s modulus and yield strength. We show empirically that our approach achieves high accuracy, outperforming a baseline, ResNet-34, in estimating the mechanical properties. We then use SHAP and Integrated Gradients, two post-hoc XAI methods, to explain the predictions, showing that the CNNs use the critical geometrical features that influence the composites’ behaviour, thus allowing engineers to verify that the models are trustworthy by representing the science of composites.

ECAI Conference 2025 Conference Paper

Exploring the Effect of Explanation Content and Format on User Comprehension and Trust in Healthcare

• Antonio Rago 0001
• Bence Pálfi
• Purin Sukpanichnant
• Kavyesh Vivek
• Hannibal Nabli
• Olga Kostopoulou
• James Kinross
• Francesca Toni

AI-driven tools for healthcare are widely acknowledged as potentially beneficial to health practitioners and patients, e. g. the QCancer regression tool for cancer risk prediction. However, for these tools to be trusted, they need to be supplemented with explanations. We examine how explanations’ content and format affect user comprehension and trust when explaining QCancer’s predictions. Regarding content, we deploy the SHAP and Occlusion-1 explanation methods. Regarding format, we present SHAP explanations, conventionally, as charts (SC) and Occlusion-1 explanations as charts (OC) as well as text (OT), to which their simpler nature lends itself. We conduct experiments with two sets of stakeholders: the general public (representing patients) and medical students (representing healthcare practitioners). Our experiments showed higher subjective comprehension and trust for Occlusion-1 over SHAP explanations based on content. However, when controlling for format, only OT outperformed SC, suggesting this trend is driven by preferences for text. Other findings corroborated that explanation format, rather than content, is often the critical factor.

AAMAS Conference 2025 Conference Paper

Free Argumentative Exchanges for Explaining Image Classifiers

• Avinash Kori
• Antonio Rago
• Francesca Toni

Deep learning models are powerful image classifiers but their opacity hinders their trustworthiness. Explanation methods for capturing the reasoning process within these classifiers faithfully and in a clear manner are scarce, due to their sheer complexity and size. We provide a solution for this problem by defining a novel method for explaining the outputs of image classifiers with debates between two agents, each arguing for a particular class. We obtain these debates as concrete instances of Free Argumentative eXchanges (FAXs), a novel argumentation-based multi-agent framework allowing agents to internalise opinions by other agents differently than originally stated. We define two metrics (consensus and persuasion rate) to assess the usefulness of FAXs as argumentative explanations for image classifiers. We then conduct a number of empirical experiments showing that FAXs perform well along these metrics as well as being more faithful to the image classifiers than conventional, non-argumentative explanation methods. All our implementations can be found at https: //github. com/koriavinash1/FAX.

AAMAS Conference 2025 Conference Paper

Greedy ABA Learning for Case-Based Reasoning

• Emanuele De Angelis
• Maurizio Proietti
• Francesca Toni

ABA Learning is a form of logic-based learning, producing, from examples and background knowledge, symbolic representations in the form of assumption-based argumentation (ABA) frameworks that naturally encode conflicts emerging from generalising the examples as well as their resolution. ABA Learning is based on the application of transformation rules to progressively refine an initial ABA framework (the background knowledge) guided by the examples, and is typically highly nondeterministic, with the search space underpinning the choice of applied transformation rules very large. In this paper we propose a novel ‘greedy’ variant of ABA Learning tailored to settings where the examples and background knowledge are drawn from labelled cases as in case-based reasoning. Greedy ABA Learning applies the transformation rules in a fully deterministic way. We prove that, when the casebase is ‘coherent’ (i. e. , where all cases with the same features have the same label), Greedy ABA Learning corresponds exactly with AA-CBR, another form of logic-based learning for case-based reasoning. Finally, we show that Greedy ABA Learning generalises beyond coherent casebases to deal with conflicts.

ICML Conference 2025 Conference Paper

Identifiable Object Representations under Spatial Ambiguities

• Avinash Kori
• Francesca Toni
• Ben Glocker

Modular object-centric representations are essential for human-like reasoning but are challenging to obtain under spatial ambiguities, e. g. due to occlusions and view ambiguities. However, addressing challenges presents both theoretical and practical difficulties. We introduce a novel multi-view probabilistic approach that aggregates view-specific slots to capture invariant content information while simultaneously learning disentangled global viewpoint-level information. Unlike prior single-view methods, our approach resolves spatial ambiguities, provides theoretical guarantees for identifiability, and requires no viewpoint annotations. Extensive experiments on standard benchmarks and novel complex datasets validate our method’s robustness and scalability.

AAAI Conference 2025 Conference Paper

Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts

• Lihu Chen
• Adam Dejl
• Francesca Toni

Large Language Models (LLMs) possess vast amounts of knowledge within their parameters, prompting research into methods for locating and editing this knowledge. Previous work has largely focused on locating entity-related (often single-token) facts in smaller models. However, several key questions remain unanswered: (1) How can we effectively locate query-relevant neurons in contemporary autoregressive LLMs, such as Llama and Mistral? (2) How can we address the challenge of long-form text generation? (3) Are there localized knowledge regions in LLMs? In this study, we introduce Query-Relevant Neuron Cluster Attribution (QRNCA), a novel architecture-agnostic framework capable of identifying query-relevant neurons in LLMs. QRNCA allows for the examination of long-form answers beyond triplet facts by employing the proxy task of multi-choice question answering. To evaluate the effectiveness of our detected neurons, we build two multi-choice QA datasets spanning diverse domains and languages. Empirical evaluations demonstrate that our method outperforms baseline methods significantly. Further, analysis of neuron distributions reveals the presence of visible localized regions, particularly within different domains. Finally, we show potential applications of our detected neurons in knowledge editing and neuron-based prediction.

NeSy Conference 2025 Conference Paper

Neuro-Argumentative Learning with Case-Based Reasoning

• Adam Gould
• Francesca Toni

We introduce Gradual Abstract Argumentation for Case-Based Reasoning (Gradual AA-CBR), a data-driven, neurosymbolic classification model in which the outcome is determined by an argumentation debate structure that is learned simultaneously with neural-based feature extractors. Each argument in the debate is an observed case from the training data, favouring their labelling. Cases attack or support those with opposing or agreeing labellings, with the strength of each argument and relationship learned through gradient-based methods. This argumentation debate structure provides human-aligned reasoning, improving model interpretability compared to traditional neural networks (NNs). Unlike the existing purely symbolic variant, Abstract Argumentation for Case-Based Reasoning (AA-CBR), Gradual AA-CBR is capable of multi-class classification, automatic learning of feature and data point importance, assigning uncertainty values to outcomes, using all available data points, and does not require binary features. We show that Gradual AA-CBR performs comparably to NNs whilst significantly outperforming existing AA-CBR formulations.

NeSy Conference 2025 Conference Paper

Object-Centric Neuro-Argumentative Learning

• Abdul Rahman Jacob
• Avinash Kori
• Emanuele De Angelis
• Ben Glocker
• Maurizio Proietti
• Francesca Toni

Over the last decade, as we rely more on deep learning technologies to make critical decisions, concerns regarding their safety, reliability and interpretability have emerged. We introduce a novel Neural Argumentative Learning (NAL) architecture that integrates Assumption-Based Argumentation (ABA) with deep learning for image analysis. Our architecture consists of neural and symbolic components. The former segments and encodes images into facts using object-centric learning, while the latter applies ABA learning to develop ABA frameworks enabling predictions with images. Experiments on synthetic data show that the NAL architecture can be competitive with a state-of-the-art alternative.

KR Conference 2025 Conference Paper

On Gradual Semantics for Assumption-Based Argumentation

• Anna Rapberger
• Fabrizio Russo
• Antonio Rago
• Francesca Toni

In computational argumentation, gradual semantics are fine-grained alternatives to extension-based and labelling-based semantics. They ascribe a dialectical strength to (components of) arguments sanctioning their degree of acceptability. Several gradual semantics have been studied for abstract, bipolar and quantitative bipolar argumentation frameworks (QBAFs), as well as, to a lesser extent, for some forms of structured argumentation. However, this has not been the case for assumption-based argumentation (ABA), despite it being a popular form of structured argumentation with several applications where gradual semantics could be useful. In this paper, we fill this gap and propose a family of novel gradual semantics for equipping assumptions, which are the core components in ABA frameworks, with dialectical strengths. To do so, we use bipolar set-based argumentation frameworks as an abstraction of (potentially non-flat) ABA frameworks and generalise state-of-the-art modular gradual semantics for QBAFs. We show that our gradual ABA semantics satisfy suitable adaptations of desirable properties of gradual QBAF semantics, such as balance and monotonicity. We also explore an argument-based approach that leverages established QBAF modular semantics directly, and use it as baseline. Finally, we conduct experiments with synthetic ABA frameworks to compare our gradual ABA semantics with its argument-based counterpart and assess convergence.

IJCAI Conference 2025 Conference Paper

On Independence and SCC-Recursiveness in Assumption-Based Argumentation

• Lydia Blümel
• Anna Rapberger
• Matthias Thimm
• Francesca Toni

We introduce a notion of conditional independence in (flat) assumption-based argumentation (ABA), where independence between (sets of) assumptions amounts to the presence of information about one set of assumptions not impacting the acceptability of another. We study general properties, computational complexity, and the relation to independence in abstract argumentation. In light of the high computational complexity of deciding independence, we introduce sound methods for checking independence in polynomial time via two different routes: the first utilizes the strongly connected components (SCCs) of the instantiated abstract argumentation framework; the second exploits the structure of the ABA framework directly. Along the way, we introduce the notion of SCC-recursiveness for ABA.

AAAI Conference 2025 Conference Paper

ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation

• Hamed Ayoobi
• Nico Potyka
• Francesca Toni

We propose ProtoArgNet, a novel interpretable deep neural architecture for image classification in the spirit of prototypical-part-learning as found, e.g., in ProtoPNet. While earlier approaches associate every class with multiple prototypical-parts, ProtoArgNet uses super-prototypes that combine prototypical-parts into a unified class representation. This is done by combining local activations of prototypes in an MLP-like manner, enabling the localization of prototypes and learning (non-linear) spatial relationships among them. By leveraging a form of argumentation, ProtoArgNet is capable of providing both supporting (i.e. `this looks like that') and attacking (i.e. `this differs from that') explanations. We demonstrate on several datasets that ProtoArgNet outperforms state-of-the-art prototypical-part-learning approaches. Moreover, the argumentation component in ProtoArgNet is customisable to the user's cognitive requirements by a process of sparsification, which leads to more compact explanations compared to state-of-the-art approaches.

NeurIPS Conference 2025 Conference Paper

Representation Consistency for Accurate and Coherent LLM Answer Aggregation

• Junqi Jiang
• Tom Bewley
• Salim I. Amoukou
• Francesco Leofante
• Antonio Rago
• Saumitra Mishra
• Francesca Toni

Test-time scaling improves large language models' (LLMs) performance by allocating more compute budget during inference. To achieve this, existing methods often require intricate modifications to prompting and sampling strategies. In this work, we introduce representation consistency (RC), a test-time scaling method for aggregating answers drawn from multiple candidate responses of an LLM regardless of how they were generated, including variations in prompt phrasing and sampling strategy. RC enhances answer aggregation by not only considering the number of occurrences of each answer in the candidate response set, but also the consistency of the model's internal activations while generating the set of responses leading to each answer. These activations can be either dense (raw model activations) or sparse (encoded via pretrained sparse autoencoders). Our rationale is that if the model's representations of multiple responses converging on the same answer are highly variable, this answer is more likely to be the result of incoherent reasoning and should be down-weighted during aggregation. Importantly, our method only uses cached activations and lightweight similarity computations and requires no additional model queries. Through experiments with four open-source LLMs and four reasoning datasets, we validate the effectiveness of RC for improving task performance during inference, with consistent accuracy improvements (up to 4\%) over strong test-time scaling baselines. We also show that consistency in the sparse activation signals aligns well with the common notion of coherent reasoning.

JAAMAS Journal 2024 Journal Article

Aggregating bipolar opinions through bipolar assumption-based argumentation

• Charles Dickie
• Stefan Lauren
• Francesca Toni

Abstract We introduce a novel method to aggregate bipolar argumentation frameworks expressing opinions of different parties in debates. We use Bipolar Assumption-based Argumentation (ABA) as an all-encompassing formalism for bipolar argumentation under different semantics. By leveraging on recent results on judgement aggregation in social choice theory, we prove several preservation results for relevant properties of bipolar ABA using quota and oligarchic rules. Specifically, we prove (positive and negative) results about the preservation of conflict-free, closed, admissible, preferred, complete, set-stable, well-founded and ideal extensions in bipolar ABA, as well as the preservation of acceptability, acyclicity and coherence for individual assumptions. Finally, we illustrate our methodology and results in the context of a case study on opinion aggregation for the treatment of long COVID patients.

KR Conference 2024 Conference Paper

Argumentative Causal Discovery

• Fabrizio Russo
• Anna Rapberger
• Francesca Toni

Causal discovery amounts to unearthing causal relationships amongst features in data. It is a crucial companion to causal inference, necessary to build scientific knowledge without resorting to expensive or impossible randomised control trials. In this paper, we explore how reasoning with symbolic representations can support causal discovery. Specifically, we deploy assumption-based argumentation (ABA), a well-established and powerful knowledge representation formalism, in combination with causality theories, to learn graphs which reflect causal dependencies in the data. We prove that our method exhibits desirable properties, notably that, under natural conditions, it can retrieve ground-truth causal graphs. We also conduct experiments with an implementation of our method in answer set programming (ASP) on four datasets from standard benchmarks in causal discovery, showing that our method compares well against established baselines.

KR Conference 2024 Conference Paper

CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks

• Xiang Yin
• Nico Potyka
• Francesca Toni

There is a growing interest in understanding arguments' strength in Quantitative Bipolar Argumentation Frameworks (QBAFs). Most existing studies focus on attribution-based methods that explain an argument's strength by assigning importance scores to other arguments but fail to explain how to change the current strength to a desired one. To solve this issue, we introduce counterfactual explanations for QBAFs. We discuss problem variants and propose an iterative algorithm named Counterfactual Explanations for Quantitative bipolar Argumentation frameworks (CE-QArg). CE-QArg can identify valid and cost-effective counterfactual explanations based on two core modules, polarity and priority, which help determine the updating direction and magnitude for each argument, respectively. We discuss some formal properties of our counterfactual explanations and empirically evaluate CE-QArg on randomly generated QBAFs.

KR Conference 2024 Conference Paper

Contestable AI Needs Computational Argumentation

• Francesco Leofante
• Hamed Ayoobi
• Adam Dejl
• Gabriel Freedman
• Deniz Gorur
• Junqi Jiang
• Guilherme Paulino-Passos
• Antonio Rago

AI has become pervasive in recent years, but state-of-the-art approaches predominantly neglect the need for AI systems to be contestable. Instead, contestability is advocated by AI guidelines (e. g. by the OECD) and regulation of automated decision-making (e. g. GDPR). In this position paper we explore how contestability can be achieved computationally in and for AI. We argue that contestable AI requires dynamic (human-machine and/or machine-machine) explainability and decision-making processes, whereby machines can 1. interact with humans and/or other machines to progressively explain their outputs and/or their reasoning as well as assess grounds for contestation provided by these humans and/or other machines, and 2. revise their decision-making processes to redress any issues successfully raised during contestation. Given that much of the current AI landscape is tailored to static AIs, the need to accommodate contestability will require a radical rethinking, that, we argue, computational argumentation is ideally suited to support.

KR Conference 2024 System Paper

Dialectical Reconciliation via Structured Argumentative Dialogues

• Stylianos Loukas Vasileiou
• Ashwin Kumar
• William Yeoh
• Tran Cao Son
• Francesca Toni

We present a novel framework designed to extend model reconciliation approaches, commonly used in human-aware planning, for enhanced human-AI interaction. By adopting a structured argumentation-based dialogue paradigm, our framework enables dialectical reconciliation to address knowledge discrepancies between an explainer (AI agent) and an explainee (human user), where the goal is for the explainee to understand the explainer's decision. We formally describe the operational semantics of our proposed framework, providing theoretical guarantees. We then evaluate the framework's efficacy ``in the wild'' via computational and human-subject experiments. Our findings suggest that our framework offers a promising direction for fostering effective human-AI interactions in domains where explainability is important.

IJCAI Conference 2024 Conference Paper

Explaining Arguments’ Strength: Unveiling the Role of Attacks and Supports

• Xiang Yin
• Nico Potyka
• Francesca Toni

Quantitatively explaining the strength of arguments under gradual semantics has recently received increasing attention. Specifically, several works in the literature provide quantitative explanations by computing the attribution scores of arguments. These works disregard the importance of attacks and supports, even though they play an essential role when explaining arguments' strength. In this paper, we propose a novel theory of Relation Attribution Explanations (RAEs), adapting Shapley values from game theory to offer fine-grained insights into the role of attacks and supports in quantitative bipolar argumentation towards obtaining the arguments' strength. We show that RAEs satisfy several desirable properties. We also propose a probabilistic algorithm to approximate RAEs efficiently. Finally, we show the application value of RAEs in fraud detection and large language models case studies.

ICLR Conference 2024 Conference Paper

Grounded Object-Centric Learning

• Avinash Kori
• Francesco Locatello
• Fabio De Sousa Ribeiro
• Francesca Toni
• Ben Glocker

The extraction of object-centric representations for downstream tasks is an emerging area of research. Learning grounded representations of objects that are guaranteed to be stable and invariant promises robust performance across different tasks and environments. Slot Attention (SA) learns object-centric representations by assigning objects to *slots*, but presupposes a *single* distribution from which all slots are randomly initialised. This results in an inability to learn *specialized* slots which bind to specific object types and remain invariant to identity-preserving changes in object appearance. To address this, we present *Conditional Slot Attention* (CoSA) using a novel concept of *Grounded Slot Dictionary* (GSD) inspired by vector quantization. Our proposed GSD comprises (i) canonical object-level property vectors and (ii) parametric Gaussian distributions, which define a prior over the slots. We demonstrate the benefits of our method in multiple downstream tasks such as scene generation, composition, and task adaptation, whilst remaining competitive with SA in object discovery.

NeurIPS Conference 2024 Conference Paper

Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention

• Avinash Kori
• Francesco Locatello
• Ainkaran Santhirasekaram
• Francesca Toni
• Ben Glocker
• Fabio De Sousa Ribeiro

Learning modular object-centric representations is said to be crucial for systematic generalization. Existing methods show promising object-binding capabilities empirically, but theoretical identifiability guarantees remain relatively underdeveloped. Understanding when object-centric representations can theoretically be identified is important for scaling slot-based methods to high-dimensional images with correctness guarantees. To that end, we propose a probabilistic slot-attention algorithm that imposes an aggregate mixture prior over object-centric slot representations, thereby providing slot identifiability guarantees without supervision, up to an equivalence relation. We provide empirical verification of our theoretical identifiability result using both simple 2-dimensional data and high-resolution imaging datasets.

IJCAI Conference 2024 Conference Paper

Instantiations and Computational Aspects of Non-Flat Assumption-based Argumentation

• Tuomo Lehtonen
• Anna Rapberger
• Francesca Toni
• Markus Ulbricht
• Johannes P. Wallner

Most existing computational tools for assumption-based argumentation (ABA) focus on so-called flat frameworks, disregarding the more general case. In this paper, we study an instantiation-based approach for reasoning in possibly non-flat ABA. We make use of a semantics-preserving translation between ABA and bipolar argumentation frameworks (BAFs). By utilizing compilability theory, we establish that the constructed BAFs will in general be of exponential size. To keep the number of arguments and computational cost low, we present three ways of identifying redundant arguments. Moreover, we identify fragments of ABA which admit a poly-sized instantiation. We propose two algorithmic approaches for reasoning in non-flat ABA; the first utilizes the BAF instantiation while the second works directly without constructing arguments. An empirical evaluation shows that the former outperforms the latter on many instances, reflecting the lower complexity of BAF reasoning. This result is in contrast to flat ABA, where direct approaches dominate instantiation-based solvers.

AIJ Journal 2024 Journal Article

Interval abstractions for robust counterfactual explanations

• Junqi Jiang
• Francesco Leofante
• Antonio Rago
• Francesca Toni

Counterfactual Explanations (CEs) have emerged as a major paradigm in explainable AI research, providing recourse recommendations for users affected by the decisions of machine learning models. However, CEs found by existing methods often become invalid when slight changes occur in the parameters of the model they were generated for. The literature lacks a way to provide exhaustive robustness guarantees for CEs under model changes, in that existing methods to improve CEs' robustness are mostly heuristic, and the robustness performances are evaluated empirically using only a limited number of retrained models. To bridge this gap, we propose a novel interval abstraction technique for parametric machine learning models, which allows us to obtain provable robustness guarantees for CEs under a possibly infinite set of plausible model changes Δ. Based on this idea, we formalise a robustness notion for CEs, which we call Δ-robustness, in both binary and multi-class classification settings. We present procedures to verify Δ-robustness based on Mixed Integer Linear Programming, using which we further propose algorithms to generate CEs that are Δ-robust. In an extensive empirical study involving neural networks and logistic regression models, we demonstrate the practical applicability of our approach. We discuss two strategies for determining the appropriate hyperparameters in our method, and we quantitatively benchmark CEs generated by eleven methods, highlighting the effectiveness of our algorithms in finding robust CEs.

ECAI Conference 2024 Conference Paper

Learning Brave Assumption-Based Argumentation Frameworks via ASP

• Emanuele De Angelis
• Maurizio Proietti
• Francesca Toni

Assumption-based Argumentation (ABA) is advocated as a unifying formalism for various forms of non-monotonic reasoning, including logic programming. It allows capturing defeasible knowledge, subject to argumentative debate. While, in much existing work, ABA frameworks are given up-front, in this paper we focus on the problem of automating their learning from background knowledge and positive/negative examples. Unlike prior work, we newly frame the problem in terms of brave reasoning under stable extensions for ABA. We present a novel algorithm based on transformation rules (such as Rote Learning, Folding, Assumption Introduction and Fact Subsumption) and an implementation thereof that makes use of Answer Set Programming. Finally, we compare our technique to state-of-the-art ILP systems that learn defeasible knowledge.

AAAI Conference 2024 Conference Paper

Non-flat ABA Is an Instance of Bipolar Argumentation

• Markus Ulbricht
• Nico Potyka
• Anna Rapberger
• Francesca Toni

Assumption-based Argumentation (ABA) is a well-known structured argumentation formalism, whereby arguments and attacks between them are drawn from rules, defeasible assumptions and their contraries. A common restriction imposed on ABA frameworks (ABAFs) is that they are flat, i.e. each of the defeasible assumptions can only be assumed, but not derived. While it is known that flat ABAFs can be translated into abstract argumentation frameworks (AFs) as proposed by Dung, no translation exists from general, possibly non-flat ABAFs into any kind of abstract argumentation formalism. In this paper, we close this gap and show that bipolar AFs (BAFs) can instantiate general ABAFs. To this end we develop suitable, novel BAF semantics which borrow from the notion of deductive support. We investigate basic properties of our BAFs, including computational complexity, and prove the desired relation to ABAFs under several semantics.

NMR Workshop 2024 Conference Paper

On the Correspondence of Non-flat Assumption-based Argumentation and Logic Programming with Negation as Failure in the Head

• Anna Rapberger
• Markus Ulbricht 0001
• Francesca Toni

The relation between (a fragment of) assumption-based argumentation (ABA) and logic programs (LPs) under stable model semantics is well-studied. However, for obtaining this relation, the ABA framework needs to be restricted to being flat, i. e. , a fragment where the (defeasible) assumptions can never be entailed, only assumed to be true or false. Here, we remove this restriction and show a correspondence between non-flat ABA and LPs with negation as failure in their head. We then extend this result to so-called setstable ABA semantics, originally defined for the fragment of non-flat ABA called bipolar ABA. We showcase how to define set-stable semantics for LPs with negation as failure in their head and show the correspondence to set-stable ABA semantics.

KR Conference 2024 Conference Paper

Preference-Based Abstract Argumentation for Case-Based Reasoning

• Adam Gould
• Guilherme Paulino-Passos
• Seema Dadhania
• Matthew Williams
• Francesca Toni

In the pursuit of enhancing the efficacy and flexibility of interpretable, data-driven classification models, this work introduces a novel incorporation of user-defined preferences with Abstract Argumentation and Case-Based Reasoning (CBR). Specifically, we introduce Preference-Based Abstract Argumentation for Case-Based Reasoning (which we call AA-CBR-P), allowing users to define multiple approaches to compare cases with an ordering that specifies their preference over these comparison approaches. We prove that the model inherently follows these preferences when making predictions and show that previous abstract argumentation for case-based reasoning approaches are insufficient at expressing preferences over constituents of an argument. We then demonstrate how this can be applied to a real-world medical dataset sourced from a clinical trial evaluating differing assessment methods of patients with a primary brain tumour. We show empirically that our approach outperforms other interpretable machine learning models on this dataset.

AAMAS Conference 2024 Conference Paper

Recourse under Model Multiplicity via Argumentative Ensembling

• Junqi Jiang
• Francesco Leofante
• Antonio Rago
• Francesca Toni

Model Multiplicity (MM) arises when multiple, equally performing machine learning models can be trained to solve the same prediction task. Recent studies show that models obtained under MM may produce inconsistent predictions for the same input. When this occurs, it becomes challenging to provide counterfactual explanations (CEs), a common means for offering recourse recommendations to individuals negatively affected by models’ predictions. In this paper, we formalise this problem, which we name recourse-aware ensembling, and identify several desirable properties which methods for solving it should satisfy. We show that existing ensembling methods, naturally extended in different ways to provide CEs, fail to satisfy these properties. We then introduce argumentative ensembling, deploying computational argumentation to guarantee robustness of CEs to MM, while also accommodating customisable user preferences. We show theoretically and experimentally that argumentative ensembling satisfies properties that the existing methods lack, and that the trade-offs are minimal wrt accuracy.

IJCAI Conference 2024 Conference Paper

Robust Counterfactual Explanations in Machine Learning: A Survey

• Junqi Jiang
• Francesco Leofante
• Antonio Rago
• Francesca Toni

Counterfactual explanations (CEs) are advocated as being ideally suited to providing algorithmic recourse for subjects affected by the predictions of machine learning models. While CEs can be beneficial to affected individuals, recent work has exposed severe issues related to the robustness of state-of-the-art methods for obtaining CEs. Since a lack of robustness may compromise the validity of CEs, techniques to mitigate this risk are in order. In this survey, we review works in the rapidly growing area of robust CEs and perform an in-depth analysis of the forms of robustness they consider. We also discuss existing solutions and their limitations, providing a solid foundation for future developments.

AAAI Conference 2024 Conference Paper

Targeted Activation Penalties Help CNNs Ignore Spurious Signals

• Dekai Zhang
• Matt Williams
• Francesca Toni

Neural networks (NNs) can learn to rely on spurious signals in the training data, leading to poor generalisation. Recent methods tackle this problem by training NNs with additional ground-truth annotations of such signals. These methods may, however, let spurious signals re-emerge in deep convolutional NNs (CNNs). We propose Targeted Activation Penalty (TAP), a new method tackling the same problem by penalising activations to control the re-emergence of spurious signals in deep CNNs, while also lowering training times and memory usage. In addition, ground-truth annotations can be expensive to obtain. We show that TAP still works well with annotations generated by pre-trained models as effective substitutes of ground-truth annotations. We demonstrate the power of TAP against two state-of-the-art baselines on the MNIST benchmark and on two clinical image datasets, using four different CNN architectures.

AAMAS Conference 2024 Conference Paper

The Reasons that Agents Act: Intention and Instrumental Goals

• Francis Rhys Ward
• Matt MacDermott
• Francesco Belardinelli
• Francesca Toni
• Tom Everitt

Intention is an important and challenging concept in AI. It is important because it underlies many other concepts we care about, such as agency, manipulation, legal responsibility, and blame. However, ascribing intent to AI systems is contentious, and there is no universally accepted theory of intention applicable to AI agents. We operationalise the intention with which an agent acts, relating to the reasons it chooses its decision. We introduce a formal definition of intention in structural causal influence models, grounded in the philosophy literature on intent and applicable to real-world machine learning systems. Through a number of examples and results, we show that our definition captures the intuitive notion of intent and satisfies desiderata set-out by past work. In addition, we show how our definition relates to past concepts, including actual causality, and the notion of instrumental goals, which is a core idea in the literature on safe AI agents. Finally, we demonstrate how our definition can be used to infer the intentions of reinforcement learning agents and language models from their behaviour.

NeSy Conference 2023 Conference Paper

A Roadmap for Neuro-argumentative Learning

• Maurizio Proietti
• Francesca Toni

Computational argumentation (CA) has emerged, in recent decades, as a powerful formalism for knowledge representation and reasoning in the presence of conflicting information, notably when reasoning non-monotonically with rules and exceptions. Much existing work in CA has focused, to date, on reasoning with given argumentation frameworks (AFs) or, more recently, on using AFs, possibly automatically drawn from other systems, for supporting forms of XAI. In this short paper we focus instead on the problem of learning AFs from data, with a focus on neuro-symbolic approaches. Specifically, we overview existing forms of neuro-argumentative (machine) learning, resulting from a combination of neural machine learning mechanisms and argumentative (symbolic) reasoning. We include in our overview neuro-symbolic paradigms that integrate reasoners with a natural understanding in argumentative terms, notably those capturing forms of non-monotonic reasoning in logic programming. We also outline avenues and challenges for future work in this spectrum.

ECAI Conference 2023 Conference Paper

Argument Attribution Explanations in Quantitative Bipolar Argumentation Frameworks

• Xiang Yin 0007
• Nico Potyka
• Francesca Toni

Argumentative explainable AI has been advocated by several in recent years, with an increasing interest on explaining the reasoning outcomes of Argumentation Frameworks (AFs). While there is a considerable body of research on qualitatively explaining the reasoning outcomes of AFs with debates/disputes/dialogues in the spirit of extension-based semantics, explaining the quantitative reasoning outcomes of AFs under gradual semantics has not received much attention, despite widespread use in applications. In this paper, we contribute to filling this gap by proposing a novel theory of Argument Attribution Explanations (AAEs) by incorporating the spirit of feature attribution from machine learning in the context of Quantitative Bipolar Argumentation Frameworks (QBAFs): whereas feature attribution is used to determine the influence of features towards outputs of machine learning models, AAEs are used to determine the influence of arguments towards topic arguments of interest. We study desirable properties of AAEs, including some new ones and some partially adapted from the literature to our setting. To demonstrate the applicability of our AAEs in practice, we conclude by carrying out two case studies in the scenarios of fake news detection and movie recommender systems.

ECAI Conference 2023 Conference Paper

Causal Discovery and Knowledge Injection for Contestable Neural Networks

• Fabrizio Russo 0002
• Francesca Toni

Neural networks have proven to be effective at solving machine learning tasks but it is unclear whether they learn any relevant causal relationships, while their black-box nature makes it difficult for modellers to understand and debug them. We propose a novel method overcoming these issues by allowing a two-way interaction whereby neural-network-empowered machines can expose the underpinning learnt causal graphs and humans can contest the machines by modifying the causal graphs before re-injecting them into the machines. The learnt models are guaranteed to conform to the graphs and adhere to expert knowledge, some of which can also be given up-front. By building a window into the model behaviour and enabling knowledge injection, our method allows practitioners to debug networks based on the causal structure discovered from the data and underpinning the predictions. Experiments with real and synthetic tabular data show that our method improves predictive performance up to 2. 4x while producing parsimonious networks, up to 7x smaller in the input layer, compared to SOTA regularised networks.

AAMAS Conference 2023 Conference Paper

Defining Deception in Structural Causal Games

• Francis Rhys Ward
• Francesca Toni
• Francesco Belardinelli

Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems. We focus on the problem that agents might deceive in order to achieve their goals. There are a number of existing definitions of deception in the literature on game theory and symbolic AI, but there is no overarching theory of deception for learning agents in games. We introduce a functional definition of deception in structural causal games, grounded in the philosophical literature. We present several examples to establish that our formal definition captures philosophical desiderata for deception.

FLAP Journal 2023 Journal Article

Explaining Classifiers' Outputs with Causal Models and Argumentation.

• Antonio Rago
• Fabrizio Russo
• Emanuele Albini
• Francesca Toni
• Pietro Baroni

We introduce a conceptualisation for generating argumentation frameworks (AFs) from causal models for the purpose of forging explanations for models’ outputs. The conceptualisation is based on reinterpreting properties of semantics of AFs as explanation moulds, which are means for characterising argumentative relations. We demonstrate our methodology by reinterpreting the property of bi-variate reinforcement in bipolar AFs, showing how the extracted bipolar AFs may be used as relation-based explanations for the outputs of causal models. We then evaluate our method empirically when the causal models represent (Bayesian and neural network) machine learning models for classification. The results show advantages over a popular approach from the literature, both in highlighting specific relationships between feature and classification variables and in generating counterfactual explanations with respect to a commonly used metric.

AAAI Conference 2023 Conference Paper

Explaining Random Forests Using Bipolar Argumentation and Markov Networks

• Nico Potyka
• Xiang Yin
• Francesca Toni

Random forests are decision tree ensembles that can be used to solve a variety of machine learning problems. However, as the number of trees and their individual size can be large, their decision making process is often incomprehensible. We show that their decision process can be naturally represented as an argumentation problem, which allows creating global explanations via argumentative reasoning. We generalize sufficient and necessary argumentative explanations using a Markov network encoding, discuss the relevance of these explanations and establish relationships to families of abductive explanations from the literature. As the complexity of the explanation problems is high, we present an efficient approximation algorithm with probabilistic approximation guarantees.

AAAI Conference 2023 Conference Paper

Formalising the Robustness of Counterfactual Explanations for Neural Networks

• Junqi Jiang
• Francesco Leofante
• Antonio Rago
• Francesca Toni

The use of counterfactual explanations (CFXs) is an increasingly popular explanation strategy for machine learning models. However, recent studies have shown that these explanations may not be robust to changes in the underlying model (e.g., following retraining), which raises questions about their reliability in real-world applications. Existing attempts towards solving this problem are heuristic, and the robustness to model changes of the resulting CFXs is evaluated with only a small number of retrained models, failing to provide exhaustive guarantees. To remedy this, we propose ∆-robustness, the first notion to formally and deterministically assess the robustness (to model changes) of CFXs for neural networks. We introduce an abstraction framework based on interval neural networks to verify the ∆-robustness of CFXs against a possibly infinite set of changes to the model parameters, i.e., weights and biases. We then demonstrate the utility of this approach in two distinct ways. First, we analyse the ∆-robustness of a number of CFX generation methods from the literature and show that they unanimously host significant deficiencies in this regard. Second, we demonstrate how embedding ∆-robustness within existing methods can provide CFXs which are provably robust.

NeurIPS Conference 2023 Conference Paper

Honesty Is the Best Policy: Defining and Mitigating AI Deception

• Francis Ward
• Francesca Toni
• Francesco Belardinelli
• Tom Everitt

Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems. We focus on the problem that agents might deceive in order to achieve their goals (for instance, in our experiments with language models, the goal of being evaluated as truthful). There are a number of existing definitions of deception in the literature on game theory and symbolic AI, but there is no overarching theory of deception for learning agents in games. We introduce a formaldefinition of deception in structural causal games, grounded in the philosophyliterature, and applicable to real-world machine learning systems. Several examples and results illustrate that our formal definition aligns with the philosophical and commonsense meaning of deception. Our main technical result is to provide graphical criteria for deception. We show, experimentally, that these results can be used to mitigate deception in reinforcement learning agents and language models.

KR Conference 2023 Conference Paper

Interactive Explanations by Conflict Resolution via Argumentative Exchanges

• Antonio Rago
• Hengzhi Li
• Francesca Toni

As the field of explainable AI (XAI) is maturing, calls for interactive explanations for (the outputs of) AI models are growing, but the state-of-the-art predominantly focuses on static explanations. In this paper, we focus instead on interactive explanations framed as conflict resolution between agents (i. e. AI models and/or humans) by leveraging on computational argumentation. Specifically, we define Argumentative eXchanges (AXs) for dynamically sharing, in multi-agent systems, information harboured in individual agents’ quantitative bipolar argumentation frameworks towards resolving conflicts amongst the agents. We then deploy AXs in the XAI setting in which a machine and a human interact about the machine’s predictions. We identify and assess several theoretical properties characterising AXs that are suitable for XAI. Finally, we instantiate AXs for XAI by defining various agent behaviours, e. g. capturing counterfactual patterns of reasoning in machines and highlighting the effects of cognitive biases in humans. We show experimentally (in a simulated environment) the comparative advantages of these behaviours in terms of conflict resolution, and show that the strongest argument may not always be the most effective.

ECAI Conference 2023 Conference Paper

SpArX: Sparse Argumentative Explanations for Neural Networks

• Hamed Ayoobi
• Nico Potyka
• Francesca Toni

Neural networks (NNs) have various applications in AI, but explaining their decisions remains challenging. Existing approaches often focus on explaining how changing individual inputs affects NNs’ outputs. However, an explanation that is consistent with the input-output behaviour of an NN is not necessarily faithful to the actual mechanics thereof. In this paper, we exploit relationships between multi-layer perceptrons (MLPs) and quantitative argumentation frameworks (QAFs) to create argumentative explanations for the mechanics of MLPs. Our SpArX method first sparsifies the MLP while maintaining as much of the original structure as possible. It then translates the sparse MLP into an equivalent QAF to shed light on the underlying decision process of the MLP, producing global and/or local explanations. We demonstrate experimentally that SpArX can give more faithful explanations than existing approaches, while simultaneously providing deeper insights into the actual reasoning process of MLPs.

AAMAS Conference 2022 Conference Paper

Argumentative Forecasting

• Benjamin Irwin
• Antonio Rago
• Francesca Toni

We introduce the Forecasting Argumentation Framework (FAF), a novel argumentation framework for forecasting informed by recent judgmental forecasting research. FAFs comprise update frameworks which empower (human or artificial) agents to argue over time with and about probability of scenarios, whilst flagging perceived irrationality in their behaviour with a view to improving their forecasting accuracy. FAFs include three argument types with future forecasts and aggregate the strength of these arguments to inform estimates of the likelihood of scenarios. We describe an implementation of FAFs for supporting forecasting agents.

KR Conference 2022 Conference Paper

Explaining Causal Models with Argumentation: the Case of Bi-variate Reinforcement

• Antonio Rago
• Pietro Baroni
• Francesca Toni

Causal models are playing an increasingly important role in machine learning, particularly in the realm of explainable AI. We introduce a conceptualisation for generating argumentation frameworks (AFs) from causal models for the purpose of forging explanations for the models’ outputs. The conceptualisation is based on reinterpreting desirable properties of semantics of AFs as explanation moulds, which are means for characterising the relations in the causal model argumentatively. We demonstrate our methodology by reinterpreting the property of bi-variate reinforcement as an explanation mould to forge bipolar AFs as explanations for the outputs of causal models. We perform a theoretical evaluation of these argumentative explanations, examining whether they satisfy a range of desirable explanatory and argumentative properties.

KR Conference 2022 System Paper

Forecasting Argumentation Frameworks

• Benjamin Irwin
• Antonio Rago
• Francesca Toni

We introduce Forecasting Argumentation Frameworks (FAFs), a novel argumentation-based methodology for forecasting informed by recent judgmental forecasting research. FAFs comprise update frameworks which empower (human or artificial) agents to argue over time about the probability of outcomes, e. g. the winner of an election or a fluctuation in inflation rates, whilst flagging perceived irrationality in the agents' behaviour with a view to improving their forecasting accuracy. FAFs include five argument types, amounting to standard pro/con arguments, as in bipolar argumentation, as well as novel proposal arguments and increase/decrease amendment arguments. We adapt an existing gradual semantics for bipolar argumentation to determine the aggregated dialectical strength of proposal arguments and define irrational behaviour. We then give a simple aggregation function which produces a final group forecast from rational agents' individual forecasts. We identify and study properties of FAFs, and conduct an empirical evaluation which signals FAFs' potential to increase the forecasting accuracy of participants.

IJCAI Conference 2022 Conference Paper

Logically Consistent Adversarial Attacks for Soft Theorem Provers

• Alexander Gaskell
• Yishu Miao
• Francesca Toni
• Lucia Specia

Recent efforts within the AI community have yielded impressive results towards “soft theorem proving” over natural language sentences using language models. We propose a novel, generative adversarial framework for probing and improving these models’ reasoning capabilities. Adversarial attacks in this domain suffer from the logical inconsistency problem, whereby perturbations to the input may alter the label. Our Logically consistent AdVersarial Attacker, LAVA, addresses this by combining a structured generative process with a symbolic solver, guaranteeing logical consistency. Our framework successfully generates adversarial attacks and identifies global weaknesses common across multiple target models. Our analyses reveal naive heuristics and vulnerabilities in these models’ reasoning capabilities, exposing an incomplete grasp of logical deduction under logic programs. Finally, in addition to effective probing of these models, we show that training on the generated samples improves the target model’s performance.

AAMAS Conference 2022 Conference Paper

On Agent Incentives to Manipulate Human Feedback in Multi-Agent Reward Learning Scenarios

• Francis Rhys Ward
• Francesca Toni
• Francesco Belardinelli

In settings without well-defined goals, methods for reward learning allow reinforcement learning agents to infer goals from human feedback. Existing work has discussed the problem that such agents may manipulate humans, or the reward learning process, in order to gain higher reward. We introduce the neglected problem that, in multi-agent settings, agents may have incentives to manipulate one another’s reward functions in order to change each other’s behavioral policies. We focus on the setting with humans acting alongside assistive (artificial) agents who must learn the reward function by interacting with these humans. We propose a possible solution to manipulation of human feedback in this setting: the Shared Value Prior (SVP). The SVP equips agents with an assumption that the reward functions of all humans are similar. Given this assumption, the actions of any human provide information to an agent about its reward, and so the agent is incentivised to observe these actions rather than to manipulate them. We present an expository example in which the SVP prevents manipulation.

AAMAS Conference 2021 Conference Paper

Aggregating Bipolar Opinions

• Stefan Lauren
• Francesco Belardinelli
• Francesca Toni

We introduce a novel method to aggregate Bipolar Argumentation (BA) Frameworks expressing opinions by different parties in debates. We use Bipolar Assumption-based Argumentation (ABA) as an all-encompassing formalism for BA under different semantics. By leveraging on recent results on judgement aggregation in Social Choice Theory, we prove several preservation results, both positive and negative, for relevant properties of Bipolar ABA.

AAMAS Conference 2021 Conference Paper

Argflow: A Toolkit for Deep Argumentative Explanations for Neural Networks

• Adam Dejl
• Chloe He
• Pranav Mangal
• Hasan Mohsin
• Bogdan Surdu
• Eduard Voinea
• Emanuele Albini
• Piyawat Lertvittayakumjorn

In recent years, machine learning (ML) models have been successfully applied in a variety of real-world applications. However, they are often complex and incomprehensible to human users. This can decrease trust in their outputs and render their usage in critical settings ethically problematic. As a result, several methods for explaining such ML models have been proposed recently, in particular for black-box models such as deep neural networks (NNs). Nevertheless, these methods predominantly explain outputs in terms of inputs, disregarding the inner workings of the ML model computing those outputs. We present Argflow, a toolkit enabling the generation of a variety of ‘deep’ argumentative explanations (DAXs) for outputs of NNs on classification tasks.

AIJ Journal 2021 Journal Article

Argumentative explanations for interactive recommendations

• Antonio Rago
• Oana Cocarascu
• Christos Bechlivanidis
• David Lagnado
• Francesca Toni

A significant challenge for recommender systems (RSs), and in fact for AI systems in general, is the systematic definition of explanations for outputs in such a way that both the explanations and the systems themselves are able to adapt to their human users' needs. In this paper we propose an RS hosting a vast repertoire of explanations, which are customisable to users in their content and format, and thus able to adapt to users' explanatory requirements, while being reasonably effective (proven empirically). Our RS is built on a graphical chassis, allowing the extraction of argumentation scaffolding, from which diverse and varied argumentative explanations for recommendations can be obtained. These recommendations are interactive because they can be questioned by users and they support adaptive feedback mechanisms designed to allow the RS to self-improve (proven theoretically). Finally, we undertake user studies in which we vary the characteristics of the argumentative explanations, showing users' general preferences for more information, but also that their tastes are diverse, thus highlighting the need for our adaptable RS.

IJCAI Conference 2021 Conference Paper

Argumentative XAI: A Survey

• Kristijonas Čyras
• Antonio Rago
• Emanuele Albini
• Pietro Baroni
• Francesca Toni

Explainable AI (XAI) has been investigated for decades and, together with AI itself, has witnessed unprecedented growth in recent years. Among various approaches to XAI, argumentative models have been advocated in both the AI and social science literature, as their dialectical nature appears to match some basic desirable features of the explanation activity. In this survey we overview XAI approaches built using methods from the field of computational argumentation, leveraging its wide array of reasoning abstractions and explanation delivery methods. We overview the literature focusing on different types of explanation (intrinsic and post-hoc), different models with which argumentation-based explanations are deployed, different forms of delivery, and different argumentation frameworks they use. We also lay out a roadmap for future work.

AIJ Journal 2021 Journal Article

Computational complexity of flat and generic Assumption-Based Argumentation, with and without probabilities

• Kristijonas Čyras
• Quentin Heinrich
• Francesca Toni

Reasoning with probabilistic information has recently attracted considerable attention in argumentation, and formalisms of Probabilistic Abstract Argumentation (PAA), Probabilistic Bipolar Argumentation (PBA) and Probabilistic Structured Argumentation (PSA) have been proposed. These foundational advances have been complemented with investigations on the complexity of some approaches to PAA and PBA, but not to PSA. We study the complexity of an existing form of PSA, namely Probabilistic Assumption-Based Argumentation (PABA), a powerful, implemented formalism which subsumes several forms of PAA and other forms of PSA. Specifically, we establish membership (general upper bounds) and completeness (instantiated lower bounds) of reasoning in PABA for the class FP # P (of functions with a # P -oracle for counting the solutions of an NP problem) with respect to newly introduced probabilistic verification, credulous and sceptical acceptance function problems under several ABA semantics. As a by-product necessary to establish PABA complexity results, we provide a comprehensive picture of the ABA complexity landscape (for both flat and generic, possibly non-flat ABA) for the classical decision problems of verification, existence, credulous and sceptical acceptance under those ABA semantics.

KR Conference 2021 Conference Paper

Monotonicity and Noise-Tolerance in Case-Based Reasoning with Abstract Argumentation

• Guilherme Paulino-Passos
• Francesca Toni

Recently, abstract argumentation-based models of case-based reasoning (AA-CBR in short) have been proposed, originally inspired by the legal domain, but also applicable as classifiers in different scenarios. However, the formal properties of AA-CBR as a reasoning system remain largely unexplored. In this paper, we focus on analysing the non-monotonicity properties of a regular version of AA-CBR (that we call AA-CBR_>). Specifically, we prove that AA-CBR_> is not cautiously monotonic, a property frequently considered desirable in the literature. We then define a variation of AA-CBR_> which is cautiously monotonic. Further, we prove that such variation is equivalent to using AA-CBR_> with a restricted casebase consisting of all "surprising" and "sufficient" cases in the original casebase. As a by-product, we prove that this variation of AA-CBR_> is cumulative, rationally monotonic, and empowers a principled treatment of noise in "incoherent" casebases. Finally, we illustrate AA-CBR and cautious monotonicity questions on a case study on the U. S. Trade Secrets domain, a legal casebase.

KR Conference 2020 System Paper

Argumentation as a Framework for Interactive Explanations for Recommendations

• Antonio Rago
• Oana Cocarascu
• Christos Bechlivanidis
• Francesca Toni

As AI systems become ever more intertwined in our personal lives, the way in which they explain themselves to and interact with humans is an increasingly critical research area. The explanation of recommendations is thus a pivotal functionality in a user’s experience of a recommender system (RS), providing the possibility of enhancing many of its desirable features in addition to its effectiveness (accuracy wrt users’ preferences). For an RS that we prove empirically is effective, we show how argumentative abstractions underpinning recommendations can provide the structural scaffolding for (different types of) interactive explanations (IEs), i. e. explanations supporting interactions with users. We prove formally that these IEs empower feedback mechanisms that guarantee that recommendations will improve with time, hence rendering the RS scrutable. Finally, we prove experimentally that the various forms of IE (tabular, textual and conversational) induce trust in the recommendations and provide a high degree of transparency in the RS’s functionality.

ECAI Conference 2020 Conference Paper

Data-Empowered Argumentation for Dialectically Explainable Predictions

• Oana Cocarascu
• Andria Stylianou
• Kristijonas Cyras
• Francesca Toni

Today’s AI landscape is permeated by plentiful data and dominated by powerful data-centric methods with the potential to impact a wide range of human sectors. Yet, in some settings this potential is hindered by these data-centric AI methods being mostly opaque. Considerable efforts are currently being devoted to defining methods for explaining black-box techniques in some settings, while the use of transparent methods is being advocated in others, especially when high-stake decisions are involved, as in healthcare and the practice of law. In this paper we advocate a novel transparent paradigm of Data-Empowered Argumentation (DEAr in short) for dialectically explainable predictions. DEAr relies upon the extraction of argumentation debates from data, so that the dialectical outcomes of these debates amount to predictions (e. g. classifications) that can be explained dialectically. The argumentation debates consist of (data) arguments which may not be linguistic in general but may nonetheless be deemed to be ‘arguments’ in that they are dialectically related, for instance by disagreeing on data labels. We illustrate and experiment with the DEAr paradigm in three settings, making use, respectively, of categorical data, (annotated) images and text. We show empirically that DEAr is competitive with another transparent model, namely decision trees (DTs), while also naturally providing a form of dialectical explanations.

IJCAI Conference 2020 Conference Paper

Relation-Based Counterfactual Explanations for Bayesian Network Classifiers

• Emanuele Albini
• Antonio Rago
• Pietro Baroni
• Francesca Toni

We propose a general method for generating counterfactual explanations (CFXs) for a range of Bayesian Network Classifiers (BCs), e. g. single- or multi-label, binary or multidimensional. We focus on explanations built from relations of (critical and potential) influence between variables, indicating the reasons for classifications, rather than any probabilistic information. We show by means of a theoretical analysis of CFXs’ properties that they serve the purpose of indicating (potentially) pivotal factors in the classification process, whose absence would give rise to different classifications. We then prove empirically for various BCs that CFXs provide useful information in real world settings, e. g. when race plays a part in parole violation prediction, and show that they have inherent advantages over existing explanation methods in the literature.

AAAI Conference 2019 Conference Paper

Argumentation for Explainable Scheduling

• Kristijonas Čyras
• Dimitrios Letsios
• Ruth Misener
• Francesca Toni

Mathematical optimization offers highly-effective tools for finding solutions for problems with well-defined goals, notably scheduling. However, optimization solvers are often unexplainable black boxes whose solutions are inaccessible to users and which users cannot interact with. We define a novel paradigm using argumentation to empower the interaction between optimization solvers and users, supported by tractable explanations which certify or refute solutions. A solution can be from a solver or of interest to a user (in the context of ’what-if’ scenarios). Specifically, we define argumentative and natural language explanations for why a schedule is (not) feasible, (not) efficient or (not) satisfying fixed user decisions, based on models of the fundamental makespan scheduling problem in terms of abstract argumentation frameworks (AFs). We define three types of AFs, whose stable extensions are in one-to-one correspondence with schedules that are feasible, efficient and satisfying fixed decisions, respectively. We extract the argumentative explanations from these AFs and the natural language explanations from the argumentative ones.

AAMAS Conference 2019 Conference Paper

Complexity Results and Algorithms for Bipolar Argumentation

• Amin Karamlou
• Kristijonas Čyras
• Francesca Toni

Bipolar Argumentation Frameworks (BAFs) admit several interpretations of the support relation and diverging definitions of semantics. Recently, several classes of BAFs have been captured as instances of bipolar Assumption-Based Argumentation, a class of Assumption-Based Argumentation (ABA). In this paper, we establish the complexity of bipolar ABA, and consequently of several classes of BAFs. In addition to the standard five complexity problems, we analyse the rarely-addressed extension enumeration problem too. We also advance backtracking-driven algorithms for enumerating extensions of bipolar ABA frameworks, and consequently of BAFs under several interpretations. We prove soundness and completeness of our algorithms, describe their implementation and provide a scalability evaluation. We thus contribute to the study of the as yet uninvestigated complexity problems of (variously interpreted) BAFs as well as of bipolar ABA, and provide the lacking implementations thereof.

AAMAS Conference 2019 Conference Paper

Deciding the Winner of a Debate Using Bipolar Argumentation

• Amin Karamlou
• Kristijonas Čyras
• Francesca Toni

Bipolar Argumentation Frameworks (BAFs) are an important class of argumentation frameworks useful for capturing, reasoning with, and deriving conclusions from debates. They have the potential to make solid contributions to real-world multi-agent systems and human-agent interaction in domains such as legal reasoning, healthcare and politics. Despite this fact, practical systems implementing BAFs are largely lacking. In this demonstration, we provide a software system implementing novel algorithms for calculating extensions (winning sets of arguments) of BAFs. Participants in the demonstration will be able to input their own debates into our system, and watch a graphical representation of the algorithms as they process information and decide which sets of arguments are winners of the debate.

AAMAS Conference 2019 Conference Paper

Extracting Dialogical Explanations for Review Aggregations with Argumentative Dialogical Agents

• Oana Cocarascu
• Antonio Rago
• Francesca Toni

IJCAI Conference 2019 Conference Paper

On the Responsibility for Undecisiveness in Preferred and Stable Labellings in Abstract Argumentation (Extended Abstract)

• Claudia Schulz
• Francesca Toni

Different semantics of abstract Argumentation Frameworks (AFs) provide different levels of decisiveness for reasoning about the acceptability of conflicting arguments. The stable semantics is useful for applications requiring a high level of decisiveness, as it assigns to each argument the label "accepted" or the label "rejected". Unfortunately, stable labellings are not guaranteed to exist, thus raising the question as to which parts of AFs are responsible for the non-existence. In this paper, we address this question by investigating a more general question concerning preferred labellings (which may be less decisive than stable labellings but are always guaranteed to exist), namely why a given preferred labelling may not be stable and thus undecided on some arguments. In particular, (1) we give various characterisations of parts of an AF, based on the given preferred labelling, and (2) we show that these parts are indeed responsible for the undecisiveness if the preferred labelling is not stable. We then use these characterisations to explain the non-existence of stable labellings.

IJCAI Conference 2018 Conference Paper

Argumentation-Based Recommendations: Fantastic Explanations and How to Find Them

• Antonio Rago
• Oana Cocarascu
• Francesca Toni

A significant problem of recommender systems is their inability to explain recommendations, resulting in turn in ineffective feedback from users and the inability to adapt to users’ preferences. We propose a hybrid method for calculating predicted ratings, built upon an item/aspect-based graph with users’ partially given ratings, that can be naturally used to provide explanations for recommendations, extracted from user-tailored Tripolar Argumentation Frameworks (TFs). We show that our method can be understood as a gradual semantics for TFs, exhibiting a desirable, albeit weak, property of balance. We also show experimentally that our method is competitive in generating correct predictions, compared with state-of-the-art methods, and illustrate how users can interact with the generated explanations to improve quality of recommendations.

AAAI Conference 2018 Conference Paper

How Many Properties Do We Need for Gradual Argumentation?

• Pietro Baroni
• Antonio Rago
• Francesca Toni

The study of properties of gradual evaluation methods in argumentation has received increasing attention in recent years, with studies devoted to various classes of frameworks/methods leading to conceptually similar but formally distinct properties in different contexts. In this paper we provide a systematic analysis for this research landscape by making three main contributions. First, we identify groups of conceptually related properties in the literature, which can be regarded as based on common patterns and, using these patterns, we evidence that many further properties can be considered. Then, we provide a simplifying and unifying perspective for these properties by showing that they are all implied by the parametric principles of (either strict or non-strict) balance and monotonicity. Finally, we show that (instances of) these principles are satisfied by several quantitative argumentation formalisms in the literature, thus confirming their general validity and their utility to support a compact, yet comprehensive, analysis of properties of gradual argumentation.

AIJ Journal 2018 Journal Article

On the responsibility for undecisiveness in preferred and stable labellings in abstract argumentation

• Claudia Schulz
• Francesca Toni

Different semantics of abstract Argumentation Frameworks (AFs) provide different levels of decisiveness for reasoning about the acceptability of conflicting arguments. The stable semantics is useful for applications requiring a high level of decisiveness, as it assigns to each argument the label “accepted” or the label “rejected”. Unfortunately, stable labellings are not guaranteed to exist, thus raising the question as to which parts of AFs are responsible for the non-existence. In this paper, we address this question by investigating a more general question concerning preferred labellings (which may be less decisive than stable labellings but are always guaranteed to exist), namely why a given preferred labelling may not be stable and thus undecided on some arguments. In particular, (1) we give various characterisations of parts of an AF, based on the given preferred labelling, and (2) we show that these parts are indeed responsible for the undecisiveness if the preferred labelling is not stable. We then use these characterisations to explain the non-existence of stable labellings. We present two types of characterisations, based on labellings that are more (or equally) committed than the given preferred labelling on the one hand, and based on the structure of the given AF on the other, and compare the respective AF parts deemed responsible. To prove that our characterisations indeed yield responsible parts, we use a notion of enforcement of labels through structural revision, by means of which the preferred labelling of the given AF can be turned into a stable labelling of the structurally revised AF. Rather than prescribing how this structural revision is carried out, we focus on the enforcement of labels and leave the engineering of the revision open to fulfil differing requirements of applications and information available to users.

FLAP Journal 2017 Journal Article

Assumption-based Argumentation: Disputes, Explanations, Preferences.

• Kristijonas Cyras
• Xiuyi Fan
• Claudia Schulz
• Francesca Toni

Assumption-Based Argumentation (ABA) is a form of structured argumentation with roots in non-monotonic reasoning. As in other forms of structured argumentation, notions of argument and attack are not primitive in ABA, but are instead defined in terms of other notions. In the case of ABA these other notions are those of rules in a deductive system, assumptions, and contraries. ABA is equipped with a range of computational tools, based on dispute trees and amounting to dispute derivations, and benefiting from equivalent views of the semantics of argumentation in ABA, in terms of sets of arguments and, equivalently, sets of assumptions. These computational tools can also provide the foundation for multi-agent argumentative dialogues and explanation of reasoning outputs, in various settings and senses. ABA is a flexible modelling formalism, despite its simplicity, allowing to support, in particular, various forms of non-monotonic reasoning, and reasoning with some forms of preferences and defeasible rules without requiring any additional machinery. ABA can also be naturally extended to accommodate further reasoning with preferences.

KR Conference 2016 Short Paper

ABA+: Assumption-Based Argumentation with Preferences

• Kristijonas Cyras
• Francesca Toni

We present a novel approach to account for preferences in a well known structured argumentation formalism, Assumption-Based Argumentation (ABA). The new formalism, called ABA+, incorporates object-level preferences (over assumptions) directly into the attack relation to reverse attacks. We give several basic desirable properties of ABA+.

KR Conference 2016 Short Paper

Abstract Argumentation for Case-Based Reasoning

• Kristijonas Cyras
• Francesca Toni
• Ken Satoh

We investigate case-based reasoning (CBR) problems where cases are represented by abstract factors and (positive or negative) outcomes, and an outcome for a new case, represented by abstract factors, needs to be established. To this end, we employ abstract argumentation (AA) and propose a novel methodology for CBR, called AA-CBR. The argumentative formulation naturally allows to characterise the computation of an outcome as a dialogical process between a proponent and an opponent, and can also be used to extract explanations for why an outcome for a new case is (not) computed. Example 1. Alice has bought a chair from an online retailer, but wants to return it and get a refund. The retailer has a system, where a customer can claim for a refund by providing factual information about the situation. In Alice’s case: she does not like the chair (factor A); she has used the chair (factor B); the chair shows no signs of wear and tear (C); Alice had the chair for more than 30 days (D). So an outcome for Alice’s case {A, B, C, D} needs to be established. By default, the retailer will provide no refund (−) when no factors are present. The retailer has a case base CB containing previous cases together with outcomes, e. g. consisting of: a case ({A}, +) with the outcome ‘refund’ (+) if the customer does not like the chair; ({A, B}, −) sustaining no refund if in addition the customer has used the chair; and ({A, B, C}, +) when in further addition the chair is in a good condition. The outcome of the new (Alice’s) case depends on the past cases most similar to the new case: since ({A, B, C}, +) is the only such case, Alice should get refunded (+). But what if the case base contained ({A, D}, −)? Then there would be two nearest cases, ({A, B, C}, +) and ({A, D}, −). Would Alice be entitled to a refund?

AIJ Journal 2016 Journal Article

Argument graphs and assumption-based argumentation

• Robert Craven
• Francesca Toni

Arguments in structured argumentation are usually defined as trees, and extensions as sets of such tree-based arguments with various properties depending on the particular argumentation semantics. However, these arguments and extensions may have redundancies as well as circularities, which are conceptually and computationally undesirable. Focusing on the specific case of Assumption-Based Argumentation (ABA), we propose novel notions of arguments and admissible/grounded extensions, both defined in terms of graphs. We show that this avoids the redundancies and circularities of standard accounts, and set out the relationship to standard tree-based arguments and admissible/grounded extensions (as sets of arguments). We also define new notions of graph-based admissible/grounded dispute derivations for ABA, for determining whether specific sentences hold under the admissible/grounded semantics. We show that these new derivations are superior with respect to standard dispute derivations in that they are complete in general, rather than solely for restricted classes of ABA frameworks. Finally, we present several experiments comparing the implementation of graph-based admissible/grounded dispute derivations with implementations of standard dispute derivations, suggesting that the graph-based approach is computationally advantageous.

AAMAS Conference 2016 Conference Paper

Argumentation-Based Multi-Agent Decision Making with Privacy Preserved

• Yang Gao
• Francesca Toni
• Hao Wang
• Fanjiang Xu

We consider multi-agent decision making problems in which agents need to communicate with other agents to make socially optimal decisions but, at the same time, have some private information that they do not want to share. Abstract argumentation has been widely used in both single-agent and multi-agent decision making problems, because of its ability for reasoning with incomplete and conflicting information. In this work, we propose an abstract argumentation-based knowledge representation and communication protocol, such that agents can find socially optimal strategies by only disclosing the ‘necessary’ and ‘disclosable’ information. We prove that our protocol is sound, efficient, of perfect information security and guaranteed to terminate.

KR Conference 2016 Conference Paper

Discontinuity-Free Decision Support with Quantitative Argumentation Debates

• Antonio Rago
• Francesca Toni
• Marco Aurisicchio
• Pietro Baroni

IBIS (Issue Based Information System) provides a widely adopted approach for knowledge representation especially suitable for the challenging task of representing wicked decision problems. While many tools for visualisation and collaborative development of IBIS graphs are available, automated decision support in this context is still underdeveloped, even though it would benefit several applications. QuAD (Quantitative Argumentation Debate) frameworks are a recently proposed IBIS-based formalism encompassing automated decision support by means of an algorithm for quantifying the strength of alternative decision options, based on aggregation of the strength of their attacking and supporting arguments. The initially proposed aggregation method, however, may give rise to discontinuities. In this paper we propose a novel, discontinuity-free algorithm for computing the strength of decision options in QuAD frameworks. We prove that this algorithm features several desirable properties and we compare the two aggregation methods, showing that both may be appropriate in the context of different application scenarios.

AAMAS Conference 2016 Conference Paper

On the Interplay between Games, Argumentation and Dialogues

• Xiuyi Fan
• Francesca Toni

Game theory, argumentation and dialogues all address problems concerning inter-agent interaction, but from different perspectives. In this paper, we contribute to the study of the interplay between these fields. In particular, we show that by mapping games in normal form into structured argumentation, computing dominant solutions and Nash equilibria is equivalent to computing admissible sets of arguments. Moreover, when agents lack complete information, computing dominant solutions/Nash equilibria is equivalent to constructing successful (argumentation-based) dialogues. Finally, we study agents’ behaviour in these dialogues in reverse game-theoretic terms and show that, using specific notions of utility, agents engaged in (argumentation-based) dialogues are guaranteed to be truthful and disclose relevant information, and thus can converge to dominant solutions/Nash equilibria of the original games even under incomplete information.

EUMAS Conference 2015 Conference Paper

Identifying Malicious Behavior in Multi-party Bipolar Argumentation Debates

• Dionysios Kontarinis
• Francesca Toni

Abstract Lately, several works have analyzed potential uses of argumentation in multi-party debates. Usually, the focus of such works is the computation of a collectively “correct” outcome, a challenging task even when the debate’s users truthfully express their beliefs. This work focuses on debates where some users may exhibit specific types of “malicious” behavior: they may lie (by making statements they do not believe to hold) and they may hide valuable information (by not making relevant statements they believe to hold). Our approach is the following: firstly, we define “user attributes” which capture different aspects of a user’s behavior in a debate (how active, how opinionated and how classifiable a user has been); then, we build and test experimentally hypotheses that, from the values of these attributes, can predict whether a user has lied and/or hidden valuable information.

AAAI Conference 2015 Conference Paper

Logic Programming in Assumption-Based Argumentation Revisited – Semantics and Graphical Representation

• Claudia Schulz
• Francesca Toni

Logic Programming and Argumentation Theory have been existing side by side as two separate, yet related, techniques in the field of Knowledge Representation and Reasoning for many years. When Assumption-Based Argumentation (ABA) was first introduced in the nineties, the authors showed how a logic program can be encoded in an ABA framework and proved that the stable semantics of a logic program corresponds to the stable extension semantics of the ABA framework encoding this logic program. We revisit this initial work by proving that the 3-valued stable semantics of a logic program coincides with the complete semantics of the encoding ABA framework, and that the L-stable semantics of this logic program coincides with the semi-stable semantics of the encoding ABA framework. Furthermore, we show how to graphically represent the structure of a logic program encoded in an ABA framework and that not only logic programming and ABA semantics but also Abstract Argumentation semantics can be easily applied to a logic program using these graphical representations.

AAAI Conference 2015 Conference Paper

On Computing Explanations in Argumentation

• Xiuyi Fan
• Francesca Toni

Argumentation can be viewed as a process of generating explanations. However, existing argumentation semantics are developed for identifying acceptable arguments within a set, rather than giving concrete justifications for them. In this work, we propose a new argumentation semantics, related admissibility, designed for giving explanations to arguments in both Abstract Argumentation and Assumption-based Argumentation. We identify different types of explanations defined in terms of the new semantics. We also give a correct computational counterpart for explanations using dispute forests.

IJCAI Conference 2015 Conference Paper

Potential Based Reward Shaping for Hierarchical Reinforcement Learning

• Yang Gao
• Francesca Toni

Hierarchical Reinforcement Learning (HRL) outperforms many ‘flat’ Reinforcement Learning (RL) algorithms in some application domains. However, HRL may need longer time to obtain the optimal policy because of its large action space. Potential Based Reward Shaping (PBRS) has been widely used to incorporate heuristics into flat RL algorithms so as to reduce their exploration. In this paper, we investigate the integration of PBRS and HRL, and propose a new algorithm: PBRS-MAXQ- 0. We prove that under certain conditions, PBRS- MAXQ-0 is guaranteed to converge. Empirical results show that PBRS-MAXQ-0 significantly outperforms MAXQ-0 given good heuristics, and can converge even when given misleading heuristics.

AIJ Journal 2014 Journal Article

A general framework for sound assumption-based argumentation dialogues

• Xiuyi Fan
• Francesca Toni

We propose a formal model for argumentation-based dialogues between agents, using assumption-based argumentation (ABA) as the underlying argumentation framework. Thus, the dialogues amount to conducting an argumentation process in ABA. The model is given in terms of ABA-specific utterances, debate trees and forests implicitly built during and drawn from dialogues, legal-move functions (amounting to protocols) and outcome functions. The model is generic in that it is not restricted to any specific dialogue types and can be used to support a wide range thereof. We prove a formal connection between dialogues and three well-known argumentation semantics (i. e. grounded, admissible and ideal extensions), by giving soundness results for our dialogue models with respect to these semantics. Thus, our dialogues can be seen as a distributed mechanism for successfully determining acceptability of claims (with respect to the semantics considered), while constructing argumentation frameworks and arguments for these claims.

ECAI Conference 2014 Conference Paper

Argumentation Accelerated Reinforcement Learning for Cooperative Multi-Agent Systems

• Yang Gao 0021
• Francesca Toni

Multi-Agent Learning is a complex problem, especially in real-time systems. We address this problem by introducing Argumentation Accelerated Reinforcement Learning (AARL), which provides a methodology for defining heuristics, represented by arguments, and incorporates these heuristics into Reinforcement Learning (RL) by using reward shaping. We define AARL via argumentation and prove that it can coordinate independent cooperative agents that have a shared goal but need to perform different actions. We test AARL empirically in a popular RL testbed, RoboCup Takeaway, and show that it significantly improves upon standard RL.

ECAI Conference 2014 Conference Paper

On Computing Explanations in Abstract Argumentation

• Xiuyi Fan
• Francesca Toni

Argumentation can be viewed as a process of generating explanations. We propose a new argumentation semantics, related admissibility, for closely capturing explanations in Abstract Argumentation, and distinguish between compact and verbose explanations. We show that dispute forests, composed of dispute trees, can be used to correctly compute these explanations.

AIJ Journal 2013 Journal Article

A generalised framework for dispute derivations in assumption-based argumentation

• Francesca Toni

Assumption-based argumentation is a general-purpose argumentation framework with well-understood theoretical foundations and viable computational mechanisms (in the form of dispute derivations), as well as several applications. However, the existing computational mechanisms have several limitations, hindering their deployment in practice: (i) they are defined in terms of implicit parameters, that nonetheless need to be instantiated at implementation time; (ii) they are variations (for computing different semantics) of one another, but still require different implementation efforts; (iii) they reduce the problem of computing arguments to the problem of computing assumptions supporting these arguments, even though applications of argumentation require a justification of claims in terms of explicit arguments and attacks between them. In this context, the contribution of this paper is two-fold. Firstly, we provide a unified view of the existing (GB-, AB- and IB-)dispute derivations (for computation under the grounded, admissible and ideal semantics, respectively), by obtaining them as special instances of a single notion of X-dispute derivations that, in addition, renders explicit the implicit parameters in the original dispute derivations. Thus, X-dispute derivations address issues (i) and (ii). Secondly, we define structured X-dispute derivations, extending X-dispute derivations by computing explicitly the underlying arguments and attacks, in addition to assumptions. Thus, structured X-dispute derivations also address issue (iii). We prove soundness and completeness results for appropriate instances of (structured) X-dispute derivations, w. r. t. the grounded, admissible and ideal semantics, thus laying the necessary theoretical foundations for deployability thereof.

KER Journal 2013 Journal Article

On the integration of trust with negotiation, argumentation and semantics

• Piero Bonatti
• Eugenio Oliveira
• Jordi Sabater-Mir
• Carles Sierra
• Francesca Toni

Abstract Agreement Technologies are needed for autonomous agents to come to mutually acceptable agreements, typically on behalf of humans. These technologies include trust computing, negotiation, argumentation and semantic alignment. In this paper, we identify a number of open questions regarding the integration of computational models and tools for trust computing with negotiation, argumentation and semantic alignment. We consider these questions in general and in the context of applications in open, distributed settings such as the grid and cloud computing.

ECAI Conference 2012 Conference Paper

Agent Strategies for ABA-based Information-seeking and Inquiry Dialogues

• Xiuyi Fan
• Francesca Toni

Much research has been devoted to the use of argumentation to support inter-agent dialogues. Here, we contribute to this line of research by investigating the strategic behaviour of agents in argumentation-based dialogues, using Assumption-Based-Argumentation (ABA) as the underlying framework. We will focus on information-seeking and inquiry dialogues, giving formalisations thereof and showing how they can be supported by specific classes of strategy-move functions for agents to select suitable utterances.

ECAI Conference 2012 Conference Paper

Argumentation-Based Reinforcement Learning for RoboCup Soccer Keepaway

• Yang Gao 0021
• Francesca Toni
• Robert Craven

Reinforcement Learning (RL) suffers from several difficulties when applied to domains with no obvious goal state defined; this leads to inefficiency in RL algorithms. In this paper we consider a solution within the context of a widely-used testbed for RL, that of RoboCup Keepaway soccer. We introduce Argumentation-Based RL (ABRL), using methods from argumentation theory to integrate domain knowledge, represented by arguments, into the SMDP algorithm for RL by using potential-based reward shaping. Empirical results show that ABRL outperforms the original SMDP algorithm, for this game, by improving the optimal performance.

KR Conference 2012 Short Paper

Efficient Support for Medical Argumentation

• Robert Craven
• Francesca Toni
• Adrian Hadad
• Matthew Williams

IJCAI Conference 2011 Conference Paper

Assumption-Based Argumentation Dialogues

• Xiuyi Fan
• Francesca Toni

We propose a formal model for argumentationbased dialogues between agents, using assumptionbased argumentation (ABA). The model is given in terms of ABA-specific utterances, trees drawn from dialogues and legal-move and outcome functions. We prove a formal connection between these dialogues and argumentation semantics. We illustrate persuasion as an application of the dialogue model.

AAMAS Conference 2011 Conference Paper

Collaborative Diagnosis of Exceptions to Contracts

• Ouml; zg
• uuml; r Kafal
• #X131;
• Francesca Toni
• Paolo Torroni

Exceptions constitute a great deal of autonomous process execution. In order to resolve an exception, several participants should collaborate and exchange knowledge. We believe that argumentation technologies lend themselves very well to be used in this context, both for elaborating on possible causes of exceptions, and for exchanging the result of such elaboration. We propose an open and modular multi-agent framework for handling exceptions using agent dialogues and assumption-based argumentation as the underlying logic.

AAMAS Conference 2011 Conference Paper

Conflict Resolution with Argumentation Dialogues

• Xiuyi Fan
• Francesca Toni

Conflicts exist in multi-agent systems for a number of reasons: agents have different interests and desires; agents hold different beliefs; agents make different assumptions. To resolve conflicts, agents need to better convey information to each other and facilitate fair negotiations yielding jointly agreeable outcomes. We present a two-agent, dialogical conflict resolution scheme developed with the Assumption-Based Argumentation (ABA) framework.

AAMAS Conference 2010 Conference Paper

Combining statistics and arguments to compute trust

• Paul-Amaury Matt
• Maxime Morge
• Francesca Toni

We propose a method for constructing Dempster-Shafer belief functions modeling the trust of a given agent (the evaluator) in another (the target) by combining statistical information concerning the past behaviour of the target and arguments concerning the target's expected behaviour. Thesearguments are built from current and past contracts betweenevaluator and target. We prove that our method extends astandard computational method for trust that relies uponstatistical information only. We observe experimentally thatthe two methods have identical predictive performance whenthe evaluator is highly "cautious", but our method gives asignificant increase when the evaluator is not or is only moderately "cautious". Finally, we observe experimentally thattarget agents are more motivated to honour contracts whenevaluated using our model of trust than when trust is computed on a purely statistical basis.

JELIA Conference 2008 Conference Paper

A Game-Theoretic Measure of Argument Strength for Abstract Argumentation

• Paul-Amaury Matt
• Francesca Toni

Abstract Abstract argumentation (Dung 1995) is a theory of dialectic that allows us to formalise and study various notions of argument acceptability. We depart from this standard approach and formalise a measure of argument strength by applying the concept of value of a game, as defined in Game Theory (von Neumann 1928). The measure thus obtained satisfies a number of intuitively appealing properties that can be derived mathematically from the minimax theorem.

AAMAS Conference 2008 Conference Paper

Argumentation-based agents for eProcurement (Short Paper)

• Paul-Amaury Matt
• Francesca Toni
• Thanassis Stournaras
• Dimitris Dimitrelos

JAAMAS Journal 2008 Journal Article

Computational logic-based agents

• Francesca Toni
• Jamal Bentahar

IS Journal 2007 Journal Article

Computing Arguments and Attacks in Assumption-Based Argumentation

• Dorian Gaertner
• Francesca Toni

Most computational frameworks for argumentation are based on abstract argumentation, which determines an argument's acceptability on the basis of its ability to counterattack all arguments attacking it. However, this view of argumentation doesn't address how to find arguments, identify attacks, and exploit premises. Assumption-based argumentation addresses these three issues. It's a refinement of abstract argumentation but remains general purpose, nonetheless. Rather than considering arguments to be a primitive concept, assumption-based argumentation defines them as backward deductions (using sets of rules in an underlying logic) supported by sets of assumptions. This approach reduces the notion of an attack against an argument to that of deduction of a contrary of an assumption.

AAMAS Conference 2007 Conference Paper

Infinitesimal Nash Transfers for Resource Allocation in Strong Social Alliances

• PaulAmaury Matt
• Francesca Toni

We introduce a distributed and tractable mechanism for the allocation of continuously divisible resources to agents, that locally maximises the (Nash) product of their individual welfare. The mechanism involves specific m-resources-at-a-time multilateral deals over bits of resources, termed infinitesimal Nash transfers. It provides an effective way of building "strong social alliances", where in a social alliance agents fully cooperate for the global interest of society, and a strong social alliance has near-optimal utilitarian and egalitarian social welfare, as understood in social choice and welfare economics. The mechanism is scalable, can be distributed amongst agents and can be used to support, e. g. , fair trade.

JELIA Conference 2006 Conference Paper

A Formal Analysis of KGP Agents

• Fariba Sadri
• Francesca Toni

Abstract This paper contributes to the identification, formalisation and analysis of desirable properties of agent models in general and of the KGP model in particular. This model is specified in computational logic, and consequently lends itself well to formal analysis. We formalise three notions of welfare, in terms of goal achievement, progress, and reactive awareness, and we prove results related to these notions for KGP agents. These results broadly demonstrate the coherence of some of the design decisions in the KGP model, the need for some of its components for effectiveness in goal achievement, the extent to which the welfare of KGP agents can be shown to improve during their life-time, and the awareness of the agents of their reactions to changes in the environment.

ECAI Conference 2006 Conference Paper

Interleaving Belief Updating and Reasoning in Abductive Logic Programming

• Fariba Sadri
• Francesca Toni

Most existing work on knowledge representation and reasoning assumes that the updating of beliefs is performed off-line, and that reasoning from the beliefs is performed either before or after the beliefs are changed. This imposes that, if an update occurs while reasoning is performed, reasoning has to be stopped and re-started anew so that the update is taken into account, with an obvious wastage of reasoning effort. In this paper, we tackle the problem of performing belief updating on-line, while reasoning is taking place by means of an abductive proof procedure.

JELIA Conference 2004 Conference Paper

Abductive Logic Programming with CIFF: System Description

• Ulle Endriss
• Paolo Mancarella
• Fariba Sadri
• Giacomo Terreni
• Francesca Toni

Abstract Abduction has long been recognised as a powerful mechanism for hypothetical reasoning in the presence of incomplete knowledge. Here, we discuss the implementation of a novel abductive proof procedure, which we call CIFF, as it extends the IFF proof procedure [7] by dealing with Constraints, as in constraint logic programming.

JELIA Conference 2004 Conference Paper

The CIFF Proof Procedure for Abductive Logic Programming with Constraints

• Ulle Endriss
• Paolo Mancarella
• Fariba Sadri
• Giacomo Terreni
• Francesca Toni

Abstract We introduce a new proof procedure for abductive logic programming and present two soundness results. Our procedure extends that of Fung and Kowalski by integrating abductive reasoning with constraint solving and by relaxing the restrictions on allowed inputs for which the procedure can operate correctly. An implementation of our proof procedure is available and has been applied successfully in the context of multiagent systems.

ECAI Conference 2004 Conference Paper

The KGP Model of Agency

• Antonis C. Kakas
• Paolo Mancarella
• Fariba Sadri
• Kostas Stathis
• Francesca Toni

AAMAS Conference 2003 Conference Paper

Aspects of Protocol Conformance in Inter-agent Dialogues

• Ulrich Endriss
• Nicolas Maudet
• Fariba Sadri
• Francesca Toni

TCS Journal 2003 Journal Article

Linearisability on datalog programs

• Foto Afrati
• Manolis Gergatsoulis
• Francesca Toni

Linear Datalog programs are programs whose clauses have at most one intensional atom in their bodies. We explore syntactic classes of Datalog programs (syntactically non-linear) which turn out to express no more than the queries expressed by linear Datalog programs. In particular, we investigate linearisability of (database queries corresponding to) piecewise linear Datalog programs and chain queries: (a) We prove that piecewise linear Datalog programs can always be transformed into linear Datalog programs, by virtue of a procedure which performs the transformation automatically. The procedure relies upon conventional logic program transformation techniques. (b) We identify a new class of linearisable chain queries, referred to as pseudo-regular, and prove their linearisability constructively, by generating, for any given pseudo-regular chain query, the Datalog program corresponding to it.

IJCAI Conference 2003 Conference Paper

Minimally intrusive negotiating agents for resource sharing

• Fariba Sadri
• Francesca Toni
• Paolo Torroni

Paolo Torroni DEIS University of Bologna V. le Risorgimento, 2 40136 Bologna, Italy ptorroni@deis. unibo. it We study the problem of agents negotiating periods of time during which they can have use of resources, thus allowing for the sharing of resources. We define a multi-stage negotiation framework where agents, in order to obtain resources, step through a sequence of stages, each characterised by an increased chance of a mutually agreeable deal but at the price of disclosing more and more information. In the sequence, the agents may agree to move to the next stage if the previous stage fails to produce a deal amongst them. In this paper, we concentrate on two early negotiation stages, characterised by minimal disclosure of information. Thus, the agents negotiating at these stages can be thought of as "minimally intrusive".

AAMAS Conference 2003 Conference Paper

On Optimal Outcomes of Negotiations over Resources

• Ulrich Endriss
• Nicolas Maudet
• Fariba Sadri
• Francesca Toni

IJCAI Conference 2003 Conference Paper

Protocol Conformance for Logic-based Agents

• Ulrich Endriss
• Nicolas Maudet
• Fariba Sadri
• Francesca Toni

An agent communication protocol specifies the "rules of encounter" governing a dialogue between agents in a multiagent system. In non-cooperative interactions (such as negotiation dialogues) occur­ ring in open societies it is crucial that agents are equipped with proper means to check, and possi­ bly enforce, conformance to protocols. We identify different levels of conformance (weak, exhaustive, and robust conformance) and explore how a spe­ cific class of logic-based agents can exploit a new representation formalism for communication proto­ cols based on simple if-then rules in order to either check conformance a priori or enforce it at runtime.

JELIA Conference 2002 Conference Paper

An Abductive Logic Programming Architecture for Negotiating Agents

• Fariba Sadri
• Francesca Toni
• Paolo Torroni

Abstract In this paper, we present a framework for agent negotiation based on abductive logic programming. The framework is based on an existing architecture for logic-based agents, and extends it by accommodating dialogues for negotiation. As an application of negotiating agents, we propose a resource-exchanging problem. The innovative contribution of this work is in the definition of an operational model, including an agent cycle and dialogue cycle, and in the results that apply in the general case of abductive agents and in the specific case of a class of agent systems.

AIJ Journal 2002 Journal Article

On the computational complexity of assumption-based argumentation for default reasoning

• Yannis Dimopoulos
• Bernhard Nebel
• Francesca Toni

Bondarenko et al. have recently proposed an abstract framework for default reasoning. Besides capturing most existing formalisms and proving that their standard semantics all coincide, the framework extends these formalisms by generalising the semantics of admissible and preferred arguments, originally proposed for logic programming only. In this paper we analyse the computational complexity of credulous and sceptical reasoning under the semantics of admissible and preferred arguments for (the propositional variant of) the instances of the abstract framework capturing theorist, circumscription, logic programming, default logic, and autoepistemic logic. Although the new semantics have been tacitly assumed to mitigate the computational hardness of default reasoning under the standard semantics of stable extensions, we show that in many cases reasoning under the admissibility and preferability semantics is computationally harder than under the standard semantics. In particular, in the case of autoepistemic logic, sceptical reasoning under preferred arguments is located at the fourth level of the polynomial hierarchy, whereas the same form of reasoning under stable extensions is located at the second level.

IJCAI Conference 1999 Conference Paper

Preferred Arguments are Harder to Compute than Stable Extensions

• Yannis Dimopoulos
• Bernhard Nebel
• Francesca Toni

Based on an abstract framework for nonmonotonic reasoning, Bondarenko et at. have extended the logic programming semantics of admissible and preferred arguments to other nonmonotonic formalisms such as circumscription, autoepisternic logic and default logic. Although the new semantics have been tacitly assumed to mitigate the computational problems of nonmonotonic reasoning under the standard semantics of stable extensions, it seems questionable whether they improve the worst-case behaviour. As a matter of fact, we show that credulous reasoning under the new semantics in propositional logic programming and prepositional default logic has the same computational complexity as under the standard semantics. Furthermore, sceptical reasoning under the admissibility semantics is easier ~ since it is trivialised to monotonic reasoning. Finally, sceptical reasoning under the preferability semantics is harder than under the standard semantics.

LOPSTR Conference 1997 Conference Paper

Synthesis of Proof Procedures for Default Reasoning

• Phan Minh Dung
• Robert A. Kowalski
• Francesca Toni

Abstract We apply logic program development technology to define abstract proof procedures, in the form of logic programs, for computing the admissibility semantics for default reasoning proposed in [2]. The proof procedures are derived from a formal specification. The derivation guarantees the soundness of the proof procedures. The completeness of the proof procedures is shown by employing a technique of symbolic execution of logic programs to compute (an instance of) a relation implied by the specification.

AILAW Journal 1996 Journal Article

Abstract argumentation

• Robert A. Kowalski
• Francesca Toni

Abstract In this paper we explore the thesis that the role of argumentation in practical reasoning in general and legal reasoning in particular is to justify the use of defeasible rules to derive a conclusion in preference to the use of other defeasible rules to derive a conflicting conclusion. The defeasibility of rules is expressed by means of non-provability claims as additional conditions of the rules. We outline an abstract approach to defeasible reasoning and argumentation which includes many existing formalisms, including default logic, extended logic programming, non-monotonic modal logic and auto-epistemic logic, as special cases. We show, in particular, that the ‘admissibility’ semantics for all these formalisms has a natural argumentation-theoretic interpretation and proof procedure, which seem to correspond well with informal argumentation. In the admissibility semantics there is only one way for one argument to attack another, namely by undermining one of its non-provability claims. In this paper, we show how other kinds of attack between arguments, specifically how rebuttal and priority attacks, can be reduced to the undermining of non-provability claims.

LOPSTR Conference 1996 Conference Paper

An Argumentation-Theoretic Approach to Logic Program Transformation

• Francesca Toni
• Robert A. Kowalski

Abstract We present a methodology for proving that any program transformation which preserves the least Herbrand model semantics when applied to sets of Horn clauses also preserves all semantics for normal logic programming that can be formulated in argumentation-theoretic terms [3, 4, 16]. These include stable model, partial stable model, preferred extension, stationary expansion, complete scenaria, stable theory, acceptability and well-founded semantics. We apply our methodology to prove that (some forms of) unfolding, folding and goal replacement preserve all these semantics. We also show the relationship of our methodology to that of Aravindan and Dung [1].