KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking

arXiv:2404.02935v1 Announce Type: cross
Abstract: This paper introduces KnowHalu, a novel approach for detecting hallucinations in text generated by large language models (LLMs), utilizing step-wise reasoning, multi-formulation query, multi-form knowledge for factual checking, and fusion-based detection mechanism. As LLMs are increasingly applied across various domains, ensuring that their outputs are not hallucinated is critical. Recognizing the limitations of existing approaches that either rely on the self-consistency check of LLMs or perform post-hoc fact-checking without considering the complexity of queries or …

abstract arxiv cs.ai cs.cl cs.lg detection domains form fusion generated hallucination hallucinations knowledge language language models large language large language models llms novel paper query reasoning text type via wise