Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations

arXiv:2404.10960v1 Announce Type: new
Abstract: A major barrier towards the practical deployment of large language models (LLMs) is their lack of reliability. Three situations where this is particularly apparent are correctness, hallucinations when given unanswerable questions, and safety. In all three cases, models should ideally abstain from responding, much like humans, whose ability to understand uncertainty makes us refrain from answering questions we don't know. Inspired by analogous approaches in classification, this study explores the feasibility and efficacy of abstaining …

abstract arxiv cases cs.ai cs.cl deployment hallucinations humans language language models large language large language models llms major practical questions reliability safety type uncertainty