6 papers
Towards an Argumentative Foundation for Evaluative AI
Xiang Yin, Tim Miller, Nico Potyka +2
Evaluative AI (EAI) has been recently proposed as a way to support human decision-making, not by producing a single recommendation, but by presenting competing hypotheses together…
Latent Debate: A Surrogate Framework for Interpreting LLM Thinking
Lihu Chen, Xiang Yin, Francesca Toni
Understanding the internal thinking process of Large Language Models (LLMs) and the cause of hallucinations remains a key challenge. To this end, we introduce latent debate, a nove…
Strength Change Explanations in Quantitative Argumentation
Timotheus Kampik, Xiang Yin, Nico Potyka +1
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…
Contestability in Quantitative Argumentation
Xiang Yin, Nico Potyka, Antonio Rago +2
Contestable AI requires that AI-driven decisions align with human preferences. While various forms of argumentation have been shown to support contestability, Edge-Weighted Quantit…
Argumentative Large Language Models for Explainable and Contestable Claim Verification
Gabriel Freedman, Adam Dejl, Deniz Gorur +3
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 us…
CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks (Technical Report)
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…