Results
- Showing results for:
- Reset all filters
Search results
-
Book chapterDe Angelis E, Proietti M, Toni F, 2026,
Learning to Contest Argumentative Claims
, Pages: 237-255Contestability is a highly desirable property for human-centric AI, ensuring that the outcomes of an AI system can be challenged, and possibly changed, when interacting with humans and/or other AI systems. In this paper we study contestability of argumentative claims obtained from Assumption-Based Argumentation (ABA) frameworks, a unifying formalism for various non-monotonic reasoning methods that can be used for explainable AI systems. Specifically, we focus on ABA frameworks that are learnt with ABA Learning, a recent approach to symbolic learning from positive and negative examples, given a background knowledge . We formally define a notion of contestation when desirable claims are rejected or undesirable claims are accepted in learnt ABA frameworks. We also show that ABA Learning can be adapted to redress issues raised by contestation so that the desirable claims are accepted and the undesirable claims are rejected. This is naturally achieved by extending the learnt ABA framework without restarting from scratch, and instead preserving as much as possible thereof by considering some of its rules defeasible. We conduct several experiments with a variety of tabular datasets to demonstrate the computational advantages of our contestable ABA Learning in comparison with re-learning from scratch.
-
Conference paperGehlot P, Rapberger A, Russo F, et al., 2025,
Heterogeneous graph neural networks for assumption-based argumentation
, The 40th Annual AAAI Conference on Artificial Intelligence, Publisher: Association for the Advancement of Artificial IntelligenceAssumption-Based Argumentation (ABA) is a powerfulstructured 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 literature, 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. Ourwork opens new avenues for scalable approximate reasoning in structured argumentation.
-
Conference paperAyoobi H, Potyka N, Rapberger A, et al., 2025,
Argumentative Debates for Transparent Bias Detection
, AAAI2026 -
Conference paperGehlot P, Rapberger A, Russo F, et al., 2025,
Heterogeneous graph neural networks for credulous acceptance of assumptions in ABA
, The Second International Workshop on Argumentation and Applications co-located with the 22nd International Conference on Principles of Knowledge Representation and Reasoning, Pages: 14-25Assumption-Based Argumentation (ABA) is a powerful structured argumentation formalism, but exact com-putation 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 use GNNs, we represent ABA frameworks via a dependency graph representation that encodes atoms and rules as nodes and distinguishessupport, derive and attack relations by heterogeneous edge labels. We propose two GNN variants—ABAGCNand ABAGAT—that stack residual heterogeneous convolution or attention blocks, respectively, to learn nodeembeddings. Our models are trained on the ICCMA2023 benchmark, augmented with synthetic ABAFs, withhyperparameters optimised via Bayesian search. Empirically, both ABAGCN and ABAGAT outperform a state-of-the-art GNN baseline that we adapt from the abstract argumentation literature, achieving node-level an F1 score up to 0.71 on the ICCMA instances. Finally, we develop a poly-time extension-reconstruction algorithm driven by our predictor: it reconstructs stable extensions with F1 above 0.85 on small ABAFs and maintains an F1 ofabout 0.58 on frameworks with 1,000 atoms. Our work opens new avenues for scalable approximate reasoning instructured argumentation.
-
Conference paperZhou K, Dejl A, Freedman G, et al., 2025,
Evaluating uncertainty quantification methods in argumentative large language models
, 2025 Conference on Empirical Methods in Natural Language Processing, Publisher: Association for Computational Linguistics, Pages: 21700-21711Research in uncertainty quantification (UQ) for large language models (LLMs) is increasingly important towards guaranteeing the reliability of this groundbreaking technology. We explore the integration of LLM UQ methods in argumentative LLMs (ArgLLMs), an explainable LLM framework for decision-making based on computational argumentation in which UQ plays a critical role. We conduct experiments to evaluate ArgLLMs’ performance on claim verification tasks when using different LLM UQ methods, inherently performing an assessment of the UQ methods’ effectiveness. Moreover, the experimental procedure itself is a novel way of evaluating the effectiveness of UQ methods, especially when intricate and potentially contentious statements are present. Our results demonstrate that, despite its simplicity, direct prompting is an effective UQ strategy in ArgLLMs, outperforming considerably more complex approaches.
-
Conference paperPeacock D - M, Potyka N, Toni F, et al., 2025,
On the impact of sparsification on quantitative argumentative explanations in neural networks
, 3rd International Workshop on Argumentation for eXplainable AI (ArgXAI@ECAI), Publisher: CEUR Workshop Proceedings, Pages: 20-35, ISSN: 1613-0073Neural Networks (NNs) are powerful decision-making tools, but their lack of explainability limits their use inhigh-stakes domains such as healthcare and criminal justice. The recent SpArX framework sparsifies NNs andmaps them to (weighted) Quantitative Bipolar Argumentation Frameworks (QBAFs) to provide an argumentative understanding of their mechanics. QBAFs can be explained by various quantitative argumentative explanation methods such as Argument Attribution Explanations (AAEs), Relation Attribution Explanations (RAEs), and Contestability Explanations (CEs) - which assign numerical scores to arguments or relations to quantify their influence on the dialectical strength of an argument to be explained. However, it remains unexplored how sparsification of NNs impacts the explanations derived from the corresponding (weighted) QBAFs. In this paper we explore two directions for impact. First, we empirically investigate how varying the sparsification levels of NNs affects the preservation of these explanations: using four datasets (Iris, Diabetes, Cancer, and COMPAS), we find that AAEs are generally well preserved, whereas RAEs are not. Then, for CEs, we find that sparsification canimprove computational efficiency in several cases. Overall, this study offers a preliminary investigation into thepotential synergy between sparsification and explanation methods, opening up new avenues for future research.
-
Conference paperJiang J, Bewley T, Amoukou S, et al., 2025,
Representation consistency for accurate and coherent LLM answer aggregation
, The Thirty-Ninth Annual Conference on Neural Information Processing Systems, Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)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.
-
Journal articleLeofante F, Artelt A, Eliades D, et al., 2025,
Explainable AI, energy and critical infrastructure systems
, AI Magazine, Vol: 46, ISSN: 0738-4602The AAAI 2025 Bridge on “Explainable AI, Energy and Critical Infrastructure Systems” was held at the Pennsylvania Convention Centre, Philadelphia, Pennsylvania, USA, on February 25, 2025. The bridge gathered researchers and practitioners, bringing together innovation research across explainable AI, energy and critical infrastructure systems so they can enhance each other. The Bridge featured five keynote presentations by experts, one tutorial, poster presentations by authors who contributed their research findings, and three breakout sessions to discuss new challenges arising at the intersection of these exciting disciplines.
-
Conference paperGao L, Muyassar H, Hunanyan Y, et al., 2025,
ADA-X: an online system for fully automated, explainable review aggregation
, Proceedings of the 27th European Conference on Artificial Intelligence (ECAI 2025) - Demo Track, Publisher: IOS Press -
Conference paperGorur D, Rago A, Toni F, 2025,
Argumentatively coherent judgmental forecasting
, 28th European Conference on Artificial Intelligence, Publisher: IOS PressJudgmental 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 iscoherent 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.
-
Conference paperRago A, Vasileiou SL, Tran S, et al., 2025,
A methodology for incompleteness-tolerant and modular gradual semantics for argumentative statement graphs
, 22nd International Conference on Principles of Knowledge Representation and Reasoning (KR 2025), Publisher: International Joint Conferences on Artificial Intelligence OrganizationGradual 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 ameaningful role in the evaluation. Second, it is modularlydefined to leverage on any GS for QBAFs. We also define aset of novel properties for our GS and study their suitabilityalongside a set of existing properties (adapted to our setting) for two instantiations of our GS, demonstrating their advantages over existing approaches.
-
Conference paperRaaghav V, Bikos D, Rago A, et al., 2025,
Explainable prediction of the mechanical properties of composites with CNNs
, The 14th Conference on Prestigious Applications of Intelligent Systems (PAIS 2025), Publisher: IOS PressComposites are amongst the most important materialsmanufactured 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 focus 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. Ourapproach 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-hocXAI 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 trust-worthy by representing the science of composites.
-
Conference paperRago A, Palfi B, Sukpanichnant P, et al., 2025,
Exploring the effect of explanation content and format on user comprehension and trust in healthcare
, The 14th Conference on Prestigious Applications of Intelligent Systems (PAIS 2025), Publisher: IOS PressAI-driven tools for healthcare are widely acknowledgedas 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 SHAP and Occlusion-1. Regarding format, we present SHAP explanations, conventionally, ascharts (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.
-
Conference paperRapberger A, Russo F, Rago A, et al., 2025,
On gradual semantics for assumption-based argumentation
, 22nd International Conference on Principles of Knowledge Representation and Reasoning (KR 2025)In computational argumentation, gradual semantics are fine-grained alternatives to extension-based and labelling-basedsemantics. 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 frame-works as an abstraction of (potentially non-flat) ABA frame-works 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 base-line. Finally, we conduct experiments with synthetic ABA frameworks to compare our gradual ABA semantics with its argument-based counterpart and assess convergence.
-
Journal articleDickie C, Lauren S, Belardinelli F, et al., 2025,
Aggregating bipolar opinions through bipolar assumption-based argumentation
, Autonomous Agents and Multi-Agent Systems, Vol: 39, ISSN: 1387-2532We introduce a novel method to aggregate Bipolar ArgumentationFrameworks expressing opinions of different parties in debates. We use BipolarAssumption-based Argumentation (ABA) as an all-encompassing formalismfor Bipolar Argumentation under different semantics. By leveraging on recentresults on judgement aggregation in Social Choice Theory, we prove severalpreservation results for relevant properties of Bipolar ABA using quota andoligarchic rules. Specifically, we prove (positive and negative) results about thepreservation of conflict-free, closed, admissible, preferred, complete, set-stable,well-founded and ideal extensions in Bipolar ABA, as well as the preservationof acceptability, acyclicity and coherence for individual assumptions. Finally,we illustrate our methodology and results in the context of a case study onopinion aggregation for the treatment of long COVID patients.
-
Conference paperFreedman G, Toni F, 2025,
Exploring the potential for large language models to demonstrate rational probabilistic beliefs
, 38th International FLAIRS Conference, Publisher: LibraryPress@UF, ISSN: 2334-0762Advances in the general capabilities of large language models (LLMs) have led to their use for information retrieval, and as components in automated decision systems. A faithful representation of probabilistic reasoning in these models may be essential to ensure trustworthy, explainable and effective performance in these tasks. Despite previous work suggesting that LLMs can perform complex reasoning and well-calibrated uncertainty quantification, we find that current versions of this class of model lack the ability to provide rational and coherent representations of probabilistic beliefs. To demonstrate this, we introduce a novel dataset of claims with indeterminate truth values and apply a number of well-established techniques for uncertainty quantification to measure the ability of LLM's to adhere to fundamental properties of probabilistic reasoning.
-
Conference paperAyoobi H, Potyka N, Toni F, 2025,
ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation
, AAAI Conference on Artificial Intelligence -
Conference paperFreedman G, Dejl A, Gorur D, et al., 2025,
Argumentative large language models for explainable and contestable claim verification
, AAAI Conference on Artificial Intelligence, Publisher: Association for the Advancement of Artificial Intelligence, Pages: 14930-14939, ISSN: 2159-5399The 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.
-
Conference paperChen L, Dejl A, Toni F, 2025,
Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts
, The 39th Annual AAAI Conference on Artificial Intelligence -
Conference paperRusso F, Toni F, 2025,
Shapley-PC: constraint-based causal structure learning with a Shapley inspired framework
, 4th Conference on Causal Learning and Reasoning (CLeaR 2025)Causal Structure Learning (CSL), also referred to as causal discovery, amounts to extracting causal relations among variables in data. CSL enables the estimation of causal effects from observational data alone, avoiding the need to perform real life experiments. Constraint-based CSL leverages conditional independence tests to perform causal discovery. We propose Shapley-PC, a novel method to improve constraint-based CSL algorithms by using Shapley values over the possible conditioning sets, to decide which variables are responsible for the observed conditional (in)dependences. We prove soundness, completeness and asymptotic consistency of Shapley-PC and run a simulationstudy showing that our proposed algorithm is superior to existing versions of PC.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.