paper-with-me

Papers

Argumentation for Explainable and Globally Contestable Decision Support with LLMs

2026-03-15 · Adam Dejl, Matthew Williams, Francesca Toni arxiv

Large language models (LLMs) exhibit strong general capabilities, but their deployment in high-stakes domains is hindered by their opacity and unpredictability. Recent work has taken meaningful steps towards addressing these issues by augmenting LLMs with post-hoc reasoning based on computational argumentation, providing faithful explanations and enabling users to contest incorrect decisions. However, this paradigm is limited to pre-defined binary choices and only supports local contestation for specific instances, leaving the underlying decision logic unchanged and prone to repeated mistakes. In this paper, we introduce ArgEval, a framework that shifts from instance-specific reasoning to structured evaluation of general decision options. Rather than mining arguments solely for individual cases, ArgEval systematically maps task-specific decision spaces, builds corresponding option ontologies, and constructs general argumentation frameworks (AFs) for each option. These frameworks can then be instantiated to provide explainable recommendations for specific cases while still supporting global contestability through modification of the shared AFs. We investigate the effectiveness of ArgEval on treatment recommendation for glioblastoma, an aggressive brain tumour, and show that it can produce explainable guidance aligned with clinical practice.

📄 PDF Abstract BibTeX arXiv:2603.14643

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation

2025-08-26 · Yuqicheng Zhu, Nico Potyka, Daniel Hernández, Yuan He 외 arxiv

Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet suffers from critical limitations in high-stakes domains -- namely, sensitivity to noisy or contradictory evide…

Fact Verification

Contestable AI needs Computational Argumentation

2024-05-17 · Francesco Leofante, Hamed Ayoobi, Adam Dejl, Gabriel Freedman 외

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 regul…

Decision Making

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

2026-02-27 · Adam Dejl, Deniz Gorur, Francesca Toni arxiv

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 …

Argumentative Large Language Models for Explainable and Contestable Claim Verification

2024-05-03 · Gabriel Freedman, Adam Dejl, Deniz Gorur, Xiang Yin 외

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 …

Claim VerificationDecision MakingDiversity

Position: Multi-Agent Algorithmic Care Systems Demand Contestability for Trustworthy AI

2026-03-21 · Truong Thanh Hung Nguyen, Hélène Fournier, Piper Jackson, Makoto Itoh 외 arxiv

Multi-agent systems (MAS) are increasingly used in healthcare to support complex decision-making through collaboration among specialized agents. Because these systems act as collective decision-makers, they raise challen…