In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation

arXiv:2403.01548v1 Announce Type: cross
Abstract: Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into the underlying mechanisms of LLM hallucinations from the perspective of inner representations, and discover a salient pattern associated with hallucinations: correct generations tend to have sharper context activations in the hidden states of the in-context tokens, compared to the incorrect ones. Leveraging this insight, we propose an entropy-based …

abstract alerts arxiv context cs.ai cs.cl cs.lg errors hallucination hallucinations language language models large language large language models llm llm hallucinations llms perspective representation study type understanding