Bruno Yun

JAIR Journal 2026 Journal Article

Bases for Weighted Gradual Semantics and Inverse Problems in Argumentation Theory

• Assaf Libman
• Nir Oren
• Bruno Yun

Weighted gradual semantics provide an acceptability degree to each argument representing its final strength, computed based on factors including the argument's background evidence, and taking into account interactions between the argument and others. We introduce five important problems linking gradual semantics and acceptability degrees. First, we re-examine the inverse problem, seeking to identify each argument's initial weights within the argumentation framework which lead to a specific final acceptability degree. Second, we ask whether the function mapping between argument weights and acceptability degrees is one-to-one. Third, we ask if this mapping is a homeomorphism so that small perturbations in weights lead to small perturbation in acceptability degrees and vice versa. Fourth, we ask whether argument weights can be found when preferences, rather than acceptability degrees for arguments are considered. Last, we consider the geometry of the space of valid acceptability degrees, asking whether ``"gaps" exist in this space. While different gradual semantics have been proposed in the literature, in this paper, and building on the geometry of the acceptability degree space, we identify a large family of weighted gradual semantics which contains many of the existing well-known semantics while maintaining desirable properties such as convergence to a unique fixed point and solving all five aforementioned problems.

AAMAS Conference 2026 Conference Paper

Bounding Acceptability Degrees and Eliciting Initial Weights in Gradual Argumentation

• Nir Oren
• Bruno Yun

Many semantics for abstract weighted argumentation assume that each argument is associated with a numerical initial weight. However, eliciting these initial weights poses several challenges: (1) accurately providing a specific numerical value is often difficult, and (2) individuals frequently confuse initial weights with acceptability degrees in the presence of other arguments. To address these issues, we propose an elicitation pipeline that allows a user to specify their believed final acceptability degree intervals for each argument. We can determine which portion (if any) of these intervals are rational, refining the intervals, or restoring rationality when the intervals are irrational. This allows us to ultimately identify possible initial weights for each argument.

AIJ Journal 2026 Journal Article

Human compliance with computational argumentation principles

• Predrag Teovanović
• Srdjan Vesic
• Bruno Yun

This paper presents a comprehensive examination of human compliance with normative principles of argumentation across two experimental studies. The first study investigated whether fundamental argumentation principles such as anonymity, independence, void precedence, and maximality align with human reasoning. Additionally, it explored whether graph-based representations of arguments facilitate better understanding and adherence to these principles compared to textual representations of arguments alone and examined the role of individual cognitive differences in compliance with these principles. Our experiments revealed that graph-based representations significantly improved compliance with argumentation principles, particularly among individuals with higher cognitive reflection. The second study replicated and extended the first study’s findings, introducing new principles such as skeptical precedence and simple reinstatement, and explored the effects of presenting arguments solely in graphical form, as well as the impact of a short tutorial on argumentation theory. The study also assessed participants’ ability to perform graphical tasks and how this influenced their compliance with normative principles. Results partially replicated the first study’s findings, confirming that graphical representations enhance compliance, but also revealed that the effect does not generalize to the new principles. We found evidence that in the absence of a graphical representation, performing graphical tasks can improve compliance with principles; especially drawing the argumentation graph. Moreover, a brief tutorial significantly improved performance on several principles, indicating that even minimal instruction can enhance understanding and compliance. However, the difficulties observed with the simple reinstatement principle hint that the participants’ intuition about the notion of defense diverges significantly from that of the researchers and that more careful thoughts must be put in crafting them. These studies collectively suggest that while argumentation principles can be intuitive to some extent, their comprehension and application are significantly influenced by the instruction given as well as by graphical representations and processes used to obtain them. These findings have important implications for the design of future argumentation-based tools and our understanding of how to bridge human reasoning and formal argumentation.

AAMAS Conference 2026 Conference Paper

Rejecting Arguments Based on Doubt in Structured Bipolar Argumentation

• Michael A. Müller
• Srdjan Vesic
• Bruno Yun

This paper develops a new approach to computational argumentation that is informed by philosophical and linguistic views. Namely, it takes into account two ideas that have received little attention in the literature on computational argumentation: First, an agent may rationally reject an argument based on mere doubt, thus not all arguments they could defend must be accepted; and, second, that it is sometimes more natural to think in terms of which individual sentences or claims an agent accepts in a debate, rather than which arguments. In order to incorporate these two ideas into a computational approach, we first define the notion of structured bipolar argumentation frameworks (SBAFs), where arguments consist of sentences and we have both an attack and a support relation between them. Then, we provide semantics for SBAFs with two features: (1) Unlike with completeness-based semantics, our semantics do not force agents to accept all defended arguments. (2) In addition to argument extensions, which give acceptable sets of arguments, we also provide semantics for language extensions that specify acceptable sets of sentences. These semantics represent reasonable positions an agent might have in a debate. Our semantics lie between the admissible and complete semantics of abstract argumentation. Further, our approach can be used to provide a new perspective on existing approaches. For instance, we can specify the conditions under which an agent can ignore support between arguments (i. e. under which the use of abstract argumentation is warranted) and we show that deductive support semantics is a special case of our approach.

FLAP Journal 2025 Journal Article

Argumentation-based Applications for Decision-making

• Srdjan Vesic
• Bruno Yun

This article examines the applications for decision-making based on argu- mentation, exploring both older and more recent techniques. We provide a comprehensive survey of decision-making techniques within the context of the argumentation framework employed (abstract, extended Dung, structured) and categorize existing frameworks based on their intended use. Special emphasis is placed on the implemented tools for decision-making, as well as visualization tools used in argumentation. The article concludes with a brief analysis of the limitations and potential future directions in this field.

AAMAS Conference 2025 Conference Paper

Impact Measures for Gradual Argumentation Semantics

• Caren Al Anaissy
• Jérôme Delobelle
• Srdjan Vesic
• Bruno Yun

Argumentation is a formalism allowing to reason with contradictory information by modeling arguments and their interactions. There are now an increasing number of gradual semantics to compute argument strengths and impact measures that have emerged to facilitate the interpretation of their outcomes. An impact measure assesses, for each argument, the impact of other arguments on its score. In this paper, we refine an existing impact measure and introduce a new impact measure rooted in Shapley values. We introduce several principles to evaluate those two impact measures w. r. t. some well-known gradual semantics. Our analysis provides deeper insights into the measures’ functionality and desirability.

AAMAS Conference 2025 Conference Paper

Leveraging Graph Structures and Large Language Models for End-to-End Synthetic Task-Oriented Dialogues

• Maya Medjad
• Hugo Imbert
• Bruno Yun
• Raphaël Szymocha
• Frédéric Armetta

Training task-oriented dialogue systems is both costly and timeconsuming, due to the need for high-quality datasets encompassing diverse intents. Traditional methods depend on extensive human annotation, while recent advancements leverage large language models (LLMs) to generate synthetic data. However, these approaches often require custom prompts or code, limiting accessibility for nontechnical users. We introduce GraphTOD, an end-to-end framework that simplifies the generation of task-oriented dialogues. Users can create dialogues by specifying transition graphs in JSON format. Our evaluation demonstrates that GraphTOD generates highquality dialogues across various domains, significantly lowering the cost and complexity of dataset creation.

ECAI Conference 2024 Conference Paper

Assisted Debate Builder with Large Language Models

• Elliot Faugier
• Frédéric Armetta
• Angela Bonifati
• Bruno Yun

We introduce ADBL2, an assisted debate builder tool. It is based on the capability of large language models to generalise and perform relation-based argument mining in a wide-variety of domains. It is the first open-source tool that leverages relation-based mining for (1) the verification of pre-established relations in a debate and (2) the assisted creation of new arguments by means of large language models. ADBL2 is highly modular and can work with any open-source large language models that are used as plugins. As a by-product, we also provide the first fine-tuned Mistral-7B large language model for relation-based argument mining, usable by ADBL2, which outperforms existing approaches for this task with an overall F1-score of 90. 59% across all domains.

AAMAS Conference 2022 Conference Paper

Chameleon - A Framework for Developing Conversational Agents for Medical Training Purposes

• Al-Hussein Abutaleb
• Bruno Yun

Objective Clinical Structured Examination (OSCE) is used to assess multiple competencies in medical pedagogy such as efficiently eliciting relevant clinical history from a patient. Clinical interviewing is done in a question and answer fashion, making it amenable to computer simulation. We introduce Chameleon, a framework to create virtual patients in an OSCE setting using the conversational agent platform Dialogflow CX. Our framework consists of a generic chatbot that is capable of answering most questions (in a classic non-specific clinical interview) and which can be expanded to capture any clinical presentation, e. g. a patient with backpain.

AAMAS Conference 2022 Conference Paper

Graphical Representation Enhances Human Compliance with Principles for Graded Argumentation Semantics

• Srdjan Vesic
• Bruno Yun
• Predrag Teovanovic

We examined principles of graded argumentation semantics (independence, anonymity, void precedence, and maximality) to explore if (a) they realistically model human reasoning, (b) graphical representation of arguments facilitates compliance with the principles, (c) there is a positive correlation between compliance with different principles, and (d) this compliance is related to cognitive reflection, need for cognition and faith in intuition. The participants (𝑁 = 96) were randomly assigned to one of two experimental conditions the graph group was presented with textual and graphical representations, while the second group was presented only with textual arguments. Our results indicate that there are major differences in the compliance with the several argumentation principles studied in this paper. However, compliance with argumentation principles was consistently better and more consistent in the graph group. Moreover, cognitive reflection correlated with compliance to some principles, but only in the graph group.

IJCAI Conference 2022 Conference Paper

Inverse Problems for Gradual Semantics

• Nir Oren
• Bruno Yun
• Srdjan Vesic
• Murilo Baptista

Gradual semantics with abstract argumentation provide each argument with a score reflecting its acceptability. Many different gradual semantics have been proposed in the literature, each following different principles and producing different argument rankings. A sub-class of such semantics, the so-called weighted semantics, takes, in addition to the graph structure, an initial set of weights over the arguments as input, with these weights affecting the resultant argument ranking. In this work, we consider the inverse problem over such weighted semantics. That is, given an argumentation framework and a desired argument ranking, we ask whether there exist initial weights such that a particular semantics produces the given ranking. The contribution of this paper are: (1) an algorithm to answer this problem, (2) a characterisation of the properties that a gradual semantics must satisfy for the algorithm to operate, and (3) an empirical evaluation of the proposed algorithm.

AAAI Conference 2020 Conference Paper

Ranking-Based Semantics for Sets of Attacking Arguments

• Bruno Yun
• Srdjan Vesic
• Madalina Croitoru

Argumentation is a process of evaluating and comparing sets of arguments. Ranking-based semantics received a lot of attention recently. All of the semantics introduced so far are applicable to binary attack relations. In this paper, we study a more general case when sets of arguments can jointly attack an argument. We generalise existing postulates for rankingbased semantics to fit this framework, define a general variant of h-categoriser, prove that it converges for every argumentation framework and study the postulates it satisfies. We also study the link between binary and hypergraph version of hcategoriser.

AAMAS Conference 2019 Conference Paper

NAKED: N-Ary Graphs from Knowledge Bases Expressed in Datalog±

• Bruno Yun
• Madalina Croitoru
• Srdjan Vesic
• Pierre Bisquert

In this demonstration paper, we introduce NAKED: a new generator for n-ary logic-based argumentation frameworks instantiated from inconsistent knowledge bases expressed using Datalog±. The tool allows to import a knowledge base in DLGP format, generate, visualise and export the corresponding argumentation hypergraph. We show its application on a use-case from the NoAW project.

AAMAS Conference 2018 Conference Paper

DAGGER: Datalog+/- Argumentation Graph GEneRator

• Bruno Yun
• Madalina Croitoru
• Srdjan Vesic
• Pierre Bisquert

We introduce DAGGER: a generator for logic based argumentation frameworks instantiated from inconsistent knowledge bases expressed using Datalog+/-. The tool allows to import a knowledge base in DLGP format and the generation and visualisation of the corresponding argumentation graph. Furthermore, the argumentation framework can also be exported in the Aspartix format.

AAMAS Conference 2018 Conference Paper

Graph Theoretical Properties of Logic Based Argumentation Frameworks

• Bruno Yun
• Madalina Croitoru
• Pierre Bisquert
• Srdjan Vesic

Argumentation frameworks instantiated from logical language allow for argument generation over real knowledge. We present some graph theoretical properties of argumentation graphs obtained from an inconsistent knowledge base expressed using existential rules.

IJCAI Conference 2018 Conference Paper

Inconsistency Measures for Repair Semantics in OBDA

• Bruno Yun
• Srdjan Vesic
• Madalina Croitoru
• Pierre Bisquert

In this paper, we place ourselves in the Ontology Based Data Access (OBDA) setting and investigate reasoning with inconsistent existential rules knowledge bases. We use the notion of inconsistency measures on sets of facts to rank and filter repairs. We propose a generic framework to answer queries by using the best repairs and study productivity and properties of such a framework.

AAMAS Conference 2017 Conference Paper

Are Ranking Semantics Sensitive to the Notion of Core?

• Bruno Yun
• Madalina Croitoru
• Pierre Bisquert