Author name cluster

Federico Cerutti

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

22 papers

1 author row

FLAP Journal 2025 Journal Article

Causation and Argumentation

Alexander Bochman
Federico Cerutti
Tjitze Rienstra

Causality is a feature in a socio-economical context rapidly moving towards an ethical use of robust artificial intelligence. The primary link between cau- sation and argumentation, especially in AI, stems from the fundamental role of causality in explanations, as argued in several works in the explainable arti- ficial intelligence literature. In this sense, theories of causation naturally sug- gest themselves as an essential component of explainable artificial intelligence. Causality also directly supports what-if and counterfactual reasoning, funda- mental components for fair, robust, and resilient use of artificial intelligence tools and systems. Because of its connection with the enquiry, persuasion, and negotiation monologues and dialogues, this article popularizes the fundamental concepts of causality for the computational argumentation research community. It also accounts for the approaches to address research questions at the heart of both argumentation and causality communities, including the connections between causal models and formal argumentation approaches.

PDF Details

AAMAS Conference 2025 Conference Paper

HAVA: Hybrid Approach to Value-Alignment through Reward Weighing for Reinforcement Learning

Kryspin Varys
Federico Cerutti
Adam Sobey
Timothy J. Norman

Our society is governed by a set of norms which together bring about the values we cherish such as safety, fairness or trustworthiness. The goal of value alignment is to create agents that not only do their tasks but through their behaviours also promote these values. Many of the norms are written as laws or rules (legal / safety norms) but even more remain unwritten (social norms). Furthermore, the techniques used to represent these norms also differ. Safety / legal norms are often represented explicitly, for example, in some logical language while social norms are typically learned and remain hidden in the parameter space of a neural network. There is a lack of approaches in the literature that could combine these various norm representations into a single algorithm. We propose a novel method that integrates these norms into the reinforcement learning process. Our method monitors the agent’s compliance with the given norms and summarizes it in a quantity we call the agent’s reputation. This quantity is used to weigh the received rewards to motivate the agent to become value aligned. We carry out a two experiments including a continuous state space traffic problem to demonstrate the importance of the written and unwritten norms and show how our method can find the value aligned policies. Furthermore, we carry out ablations to demonstrate why it is better to combine these two groups of norms rather than using either separately.

PDF

KR Conference 2024 Conference Paper

Learning Robust Reward Machines from Noisy Labels

Roko Parać
Lorenzo Nodari
Leo Ardon
Daniel Furelos-Blanco
Federico Cerutti
Alessandra Russo

This paper presents PROB-IRM, an approach that learns robust reward machines (RMs) for reinforcement learning (RL) agents from noisy execution traces. The key aspect of RM-driven RL is the exploitation of a finite-state ma- chine that decomposes the agent’s task into different sub- tasks. PROB-IRM uses a state-of-the-art inductive logic pro- gramming framework robust to noisy examples to learn RMs from noisy traces using the Bayesian posterior degree of be- liefs, thus ensuring robustness against inconsistencies. Piv- otal for the results is the interleaving between RM learning and policy learning: a new RM is learned whenever the RL agent generates a trace that is believed not to be accepted by the current RM. To speed up the training of the RL agent, PROB-IRM employs a probabilistic formulation of reward shaping that uses the posterior Bayesian beliefs derived from the traces. Our experimental analysis shows that PROB-IRM can learn (potentially imperfect) RMs from noisy traces and exploit them to train an RL agent to solve its tasks success- fully. Despite the complexity of learning the RM from noisy traces, agents trained with PROB-IRM perform comparably to agents provided with handcrafted RMs.

PDF Details DOI

AIJ Journal 2024 Journal Article

On generalized notions of consistency and reinstatement and their preservation in formal argumentation

Pietro Baroni
Federico Cerutti
Massimiliano Giacomin

We present a conceptualization providing an original domain-independent perspective on two crucial properties in reasoning: consistency and reinstatement. They emerge as a pair of dual characteristics, representing complementary requirements on the outcomes of reasoning processes. Central to our formalization are two underlying parametric relations: incompatibility and reinstatement violation. Different instances of these relations give rise to a spectrum of consistency and reinstatement scenarios. As a demonstration of versatility and expressive power of our approach we provide a characterization of various abstract argumentation semantics which are expressed as combinations of distinct consistency and reinstatement constraints. Moreover, we conduct an investigation into preserving these essential properties across different reasoning stages. Specifically, we delve into scenarios where a labelling is derived from other labellings through a synthesis function, using the synthesis of argument justification as an illustrative instance. We achieve a general characterization of consistency preservation synthesis functions, while we unveil an impossibility result concerning reinstatement preservation, leading us to explore an alternative notion to ensure feasibility. Our exploration reveals a weakness in the traditional definition of argument justification, for which we propose a refined version overcoming this limitation.

Details DOI

NeurIPS Conference 2024 Conference Paper

Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication

Olaf Lipinski
Adam J. Sobey
Federico Cerutti
Timothy J. Norman

Effective communication requires the ability to refer to specific parts of an observation in relation to others. While emergent communication literature shows success in developing various language properties, no research has shown the emergence of such positional references. This paper demonstrates how agents can communicate about spatial relationships within their observations. The results indicate that agents can develop a language capable of expressing the relationships between parts of their observation, achieving over 90% accuracy when trained in a referential game which requires such communication. Using a collocation measure, we demonstrate how the agents create such references. This analysis suggests that agents use a mixture of non-compositional and compositional messages to convey spatial relationships. We also show that the emergent language is interpretable by humans. The translation accuracy is tested by communicating with the receiver agent, where the receiver achieves over 78% accuracy using parts of this lexicon, confirming that the interpretation of the emergent language was successful.

PDF Details DOI

FLAP Journal 2023 Journal Article

A Formal Argumentation Exercise on the Karadžić Trial Judgment.

Federico Cerutti
Yvonne McDermott Rees

We present the methodology and the results of an application of argumentation theory to map the evidence and arguments as to whether Radovan Karadžić, President of the Serb Republic, possessed the requisite mens rea — the knowledge of wrongdoing that constitutes part of a crime — for genocide in Srebrenica. To evaluate the strengths and weaknesses of Trial Chamber’s findings in the publicly available judgment, we used argumentation-based techniques available in the CISpaces.org tool. The results of our analysis were submitted to the Appeals Chamber in the same case as an amicus curiæ brief, to assist the Appeals Chamber in its consideration of whether the Trial Chamber erred in finding that Karadžić possessed the requisite mens rea.

PDF Details

FLAP Journal 2023 Journal Article

Decomposing Semantics in Abstract Argumentation.

Pietro Baroni
Federico Cerutti
Massimiliano Giacomin

The paper introduces a general model for the investigation on decomposability in abstract argumentation, i.e. the possibility of determining the labellings prescribed by a semantics based on evaluations of local functions in subframeworks. By exploiting this model, the paper shows the range of decomposable semantics with varying degrees of local information. A constructive procedure for identifying local functions is then devised, encompassing two kinds of local functions, both of them able to enforce decomposability whenever the semantics is decomposable. As an example of application, the decomposability properties of stable, grounded and preferred semantics are analyzed when local information concerning close neighbors is available.

PDF Details

AAMAS Conference 2023 Conference Paper

Visualizing Logic Explanations for Social Media Moderation

Marc Roig Vilamala
Dave Braines
Federico Cerutti
Alun Preece

Autonomous artificial moderators can be useful to monitor social media for content that violates platform policies, but such artificial moderators can be confidently wrong about their decisions. While creating an approach that makes no mistakes is effectively impossible, being able to generate explanations for any given decision can simplify the task of detecting when the system is wrong. In this work we present LiveEvents, a neuro-symbolic agent capable of generating explanations based on which rules have lead to its decisions. We deliver these explanations via Cogni-Sketch, which provides users with an interactive visual representation, allowing them to easily understand the explanations given by the system.

PDF

IJCAI Conference 2022 Conference Paper

Evidential Reasoning and Learning: a Survey

Federico Cerutti
Lance M. Kaplan
Murat Şensoy

When collaborating with an artificial intelligence (AI) system, we need to assess when to trust its recommendations. Suppose we mistakenly trust it in regions where it is likely to err. In that case, catastrophic failures may occur, hence the need for Bayesian approaches for reasoning and learning to determine the confidence (or epistemic uncertainty) in the probabilities of the queried outcome. Pure Bayesian methods, however, suffer from high computational costs. To overcome them, we revert to efficient and effective approximations. In this paper, we focus on techniques that take the name of evidential reasoning and learning from the process of Bayesian update of given hypotheses based on additional evidence. This paper provides the reader with a gentle introduction to the area of investigation, the up-to-date research outcomes, and the open questions still left unanswered.

PDF Details DOI

IJCAI Conference 2021 Conference Paper

Skeptical Reasoning with Preferred Semantics in Abstract Argumentation without Computing Preferred Extensions

Matthias Thimm
Federico Cerutti
Mauro Vallati

We address the problem of deciding skeptical acceptance wrt. preferred semantics of an argument in abstract argumentation frameworks, i. e. , the problem of deciding whether an argument is contained in all maximally admissible sets, a. k. a. preferred extensions. State-of-the-art algorithms solve this problem with iterative calls to an external SAT-solver to determine preferred extensions. We provide a new characterisation of skeptical acceptance wrt. preferred semantics that does not involve the notion of a preferred extension. We then develop a new algorithm that also relies on iterative calls to an external SAT-solver but avoids the costly part of maximising admissible sets. We present the results of an experimental evaluation that shows that this new approach significantly outperforms the state of the art. We also apply similar ideas to develop a new algorithm for computing the ideal extension.

PDF Details DOI

AAAI Conference 2020 Conference Paper

Uncertainty-Aware Deep Classifiers Using Generative Models

Murat Sensoy
Lance Kaplan
Federico Cerutti
Maryam Saleki

Deep neural networks are often ignorant about what they do not know and overconﬁdent when they make uninformed predictions. Some recent approaches quantify classiﬁcation uncertainty directly by training the model to output high uncertainty for the data samples close to class boundaries or from the outside of the training distribution. These approaches use an auxiliary data set during training to represent out-ofdistribution samples. However, selection or creation of such an auxiliary data set is non-trivial, especially for high dimensional data such as images. In this work we develop a novel neural network model that is able to express both aleatoric and epistemic uncertainty to distinguish decision boundary and out-of-distribution regions of the feature space. To this end, variational autoencoders and generative adversarial networks are incorporated to automatically generate out-of-distribution exemplars for training. Through extensive analysis, we demonstrate that the proposed approach provides better estimates of uncertainty for in- and out-of-distribution samples, and adversarial examples on well-known data sets against state-ofthe-art approaches including recent Bayesian approaches for neural networks and anomaly detection methods.

PDF Details

AIJ Journal 2019 Journal Article

How we designed winning algorithms for abstract argumentation and which insight we attained

Federico Cerutti
Massimiliano Giacomin
Mauro Vallati

In this paper we illustrate the design choices that led to the development of ArgSemSAT, the winner of the preferred semantics track at the 2017 International Competition on Computational Models of Arguments (ICCMA 2017), a biennial contest on problems associated to the Dung's model of abstract argumentation frameworks, widely recognised as a fundamental reference in computational argumentation. The algorithms of ArgSemSAT are based on multiple calls to a SAT solver to compute complete labellings, and on encoding constraints to drive the search towards the solution of decision and enumeration problems. In this paper we focus on preferred semantics (and incidentally stable as well), one of the most popular and complex semantics for identifying acceptable arguments. We discuss our design methodology that includes a systematic exploration and empirical evaluation of labelling encodings, algorithmic variations and SAT solver choices. In designing the successful ArgSemSAT, we discover that: (1) there is a labelling encoding that appears to be universally better than other, logically equivalent ones; (2) composition of different techniques such as AllSAT and enumerating stable extensions when searching for preferred semantics brings advantages; (3) injecting domain specific knowledge in the algorithm design can lead to significant improvements.

Details DOI

KER Journal 2019 Journal Article

Predictive models and abstract argumentation: the case of high-complexity semantics

Mauro Vallati
Federico Cerutti
Massimiliano Giacomin

Abstract In this paper, we describe how predictive models can be positively exploited in abstract argumentation. In particular, we present two main sets of results. On one side, we show that predictive models are effective for performing algorithm selection in order to determine which approach is better to enumerate the preferred extensions of a given argumentation framework. On the other side, we show that predictive models predict significant aspects of the solution to the preferred extensions enumeration problem. By exploiting an extensive set of argumentation framework features—that is, values that summarize a potentially important property of a framework—the proposed approach is able to provide an accurate prediction about which algorithm would be faster on a given problem instance, as well as of the structure of the solution, where the complete knowledge of such structure would require a computationally hard problem to be solved. Improving the ability of existing argumentation-based systems to support human sense-making and decision processes is just one of the possible exploitations of such knowledge obtained in an inexpensive way.

Details DOI

AAAI Conference 2019 Conference Paper

Probabilistic Logic Programming with Beta-Distributed Random Variables

Federico Cerutti
Lance Kaplan
Angelika Kimmig
Murat Şensoy

We enable aProbLog—a probabilistic logical programming approach—to reason in presence of uncertain probabilities represented as Beta-distributed random variables. We achieve the same performance of state-of-the-art algorithms for highly specified and engineered domains, while simultaneously we maintain the flexibility offered by aProbLog in handling complex relational domains. Our motivation is that faithfully capturing the distribution of probabilities is necessary to compute an expected utility for effective decision making under uncertainty: unfortunately, these probability distributions can be highly uncertain due to sparse data. To understand and accurately manipulate such probability distributions we need a well-defined theoretical framework that is provided by the Beta distribution, which specifies a distribution of probabilities representing all the possible values of a probability when the exact value is unknown.

PDF Details

KR Conference 2018 Short Paper

A General Approach to Reasoning with Probabilities

Federico Cerutti
Matthias Thimm

We aim at unifying many of the aforementioned approaches and define a general methodology for reasoning with quantitative uncertainty. This allows for a general study of its properties while abstracting away from any specific instantiation. We focus on probability theory as a means for quantitative uncertain reasoning but a similar methodology can be defined by building on other formalisms such as fuzzy logic or Dempster-Shafer theory. We start by considering an arbitrary base logic and define its probabilistic augmentation by extending the syntax to allow for annotated probabilities on each formula. Therefore, a knowledge base of probabilistic augmentation consists of a set of formulas, each annotated with a probability. We define a general probabilistic semantics on top of the built-in semantics of the base logic by (1) considering each subset of the knowledge base, (2) performing ordinary inference within the subset, and (3) accumulating the inferences by taking the probabilities into account. This gives us a general methodology for defining probabilistic versions of existing knowledge representation formalisms, and is inspired by many concrete realisations such as the distribution semantics for logic programming (Sato 1995). We propose a general scheme for adding probabilistic reasoning capabilities to any knowledge representation formalism.

FLAP Journal 2017 Journal Article

Foundations of Implementations for Formal Argumentation.

Federico Cerutti
Sarah Alice Gaggl
Matthias Thimm
Johannes P. Wallner

We survey the current state of the art of general techniques, as well as specific software systems for solving tasks in abstract argumentation frameworks, structured argumentation frameworks, and approaches for visualizing and analysing argumentation. Furthermore, we discuss challenges and promising techniques such as parallel processing and approximation approaches. Finally, we address the issue of evaluating software systems empirically with links to the International Competition on Computational Models of Argumentation.

PDF Details

KR Conference 2016 Short Paper

jArgSemSAT: an Efficient Off-The-Shelf Solver for Abstract Argumentation Frameworks

Federico Cerutti
Mauro Vallati
Massimiliano Giacomin

In this report from the ﬁeld we describe jArgSemSAT, a Java re-implementation of ArgSemSAT. We show that jArgSemSAT can be easily integrated in existing argumentation systems (1) as an off-the-shelf, standalone, library; (2) as a Tweety compatible library; and (3) as a fast and robust web service freely available on the Web. The performance section shows that—despite being written in Java—jArgSemSAT is very efﬁcient w. r. t. preferred semantics, which has associated problems with high computational complexity.

AAAI Conference 2015 Conference Paper

Exploiting Parallelism for Hard Problems in Abstract Argumentation

Federico Cerutti
Ilias Tachmazidis
Mauro Vallati
Sotirios Batsakis
Massimiliano Giacomin
Grigoris Antoniou

Abstract argumentation framework (AF) is a unifying framework able to encompass a variety of nonmonotonic reasoning approaches, logic programming and computational argumentation. Yet, efficient approaches for most of the decision and enumeration problems associated to AFs are missing, thus limiting the efficacy of argumentation-based approaches in real domains. In this paper, we present an algorithm for enumerating the preferred extensions of abstract argumentation frameworks which exploits parallel computation. To this purpose, the SCC-recursive semantics definition schema is adopted, where extensions are defined at the level of specific sub-frameworks. The algorithm shows significant performance improvements in large frameworks, in terms of number of solutions found and speedup.

PDF Details

KR Conference 2014 Conference Paper

A SCC Recursive Meta-Algorithm for Computing Preferred Labellings in Abstract Argumentation

Federico Cerutti
Massimiliano Giacomin
Mauro Vallati
Marina Zanella

This paper presents a meta-algorithm for the computation of preferred labellings, based on the general recursive schema for argumentation semantics called SCC-Recursiveness. The idea is to recursively decompose a framework so as to compute semantics labellings on restricted sub-frameworks, in order to reduce the computational effort. The meta-algorithm can be instantiated with a specific “base algorithm”, applied to the base case of the recursion, which can be obtained by generalizing existing algorithms in order to compute labellings in restricted sub-frameworks. We devise for this purpose a generalization of a SAT-based algorithm, and provide an empirical investigation to show the significant improvement of performances obtained by exploiting the SCCrecursive schema.

AIJ Journal 2014 Journal Article

On the Input/Output behavior of argumentation frameworks

Pietro Baroni
Guido Boella
Federico Cerutti
Massimiliano Giacomin
Leendert van der Torre
Serena Villata

This paper tackles the fundamental questions arising when looking at argumentation frameworks as interacting components, characterized by an Input/Output behavior, rather than as isolated monolithical entities. This modeling stance arises naturally in some application contexts, like multi-agent systems, but, more importantly, has a crucial impact on several general application-independent issues, like argumentation dynamics, argument summarization and explanation, incremental computation, and inter-formalism translation. Pursuing this research direction, the paper introduces a general modeling approach and provides a comprehensive set of theoretical results putting the intuitive notion of Input/Output behavior of argumentation frameworks on a solid formal ground. This is achieved by combining three main ingredients. First, several novel notions are introduced at the representation level, notably those of argumentation framework with input, of argumentation multipole, and of replacement of multipoles within a traditional argumentation framework. Second, several relevant features of argumentation semantics are identified and formally characterized. In particular, the canonical local function provides an input-aware semantics characterization and a suite of decomposability properties are introduced, concerning the correspondences between semantics outcomes at global and local level. The third ingredient glues the former ones, as it consists of the investigation of some semantics-dependent properties of the newly introduced entities, namely S -equivalence of multipoles, S -legitimacy and S -safeness of replacements, and transparency of a semantics with respect to replacements. Altogether they provide the basis and draw the limits of sound interchangeability of multipoles within traditional frameworks. The paper develops an extensive analysis of all the concepts listed above, covering seven well-known literature semantics and taking into account various, more or less constrained, ways of partitioning an argumentation framework. Diverse examples, taken from the literature, are used to illustrate the application of the results obtained and, finally, an extensive discussion of the related literature is provided.

Details DOI

AIJ Journal 2013 Journal Article

Automata for infinite argumentation structures

Pietro Baroni
Federico Cerutti
Paul E. Dunne
Massimiliano Giacomin

The theory of abstract argumentation frameworks (afs) has, in the main, focused on finite structures, though there are many significant contexts where argumentation can be regarded as a process involving infinite objects. To address this limitation, in this paper we propose a novel approach for describing infinite afs using tools from formal language theory. In particular, the possibly infinite set of arguments is specified through the language recognized by a deterministic finite automaton while a suitable formalism, called attack expression, is introduced to describe the relation of attack between arguments. The proposed approach is shown to satisfy some desirable properties which cannot be achieved through other “naive” uses of formal languages. In particular, the approach is shown to be expressive enough to capture (besides any arbitrary finite structure) a large variety of infinite afs including two major examples from previous literature and two sample cases from the domains of multi-agent negotiation and ambient intelligence. On the computational side, we show that several decision and construction problems which are known to be polynomial time solvable in finite afs are decidable in the context of the proposed formalism and we provide the relevant algorithms. Moreover we obtain additional results concerning the case of finitary afs.

Details DOI

IJCAI Conference 2011 Conference Paper

Decision Support through Argumentation-Based Practical Reasoning

Federico Cerutti

This extended research abstract describes an argumentation-based approach to modelling articulated decision making contexts. The approach encompasses a variety of argument and attack schemes aimed at representing basic knowledge and reasoning patterns for decision support.

PDF Details DOI