Argumentative Large Language Models for Explainable and Contestable Decision-Making

arXiv:2405.02079v1 Announce Type: new
Abstract: The diversity of knowledge encoded in large language models (LLMs) and their ability to apply this knowledge zero-shot in a range of settings makes them a promising candidate for use in decision-making. However, they are currently limited by their inability to reliably provide outputs which are explainable and contestable. In this paper, we attempt to reconcile these strengths and weaknesses by introducing a method for supplementing LLMs with argumentative reasoning. Concretely, we introduce argumentative LLMs, …

abstract apply arxiv cs.ai cs.cl decision diversity however knowledge language language models large language large language models llms making them type zero-shot