KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking
This addresses the critical issue of ensuring factual accuracy in LLM outputs across various domains, representing a novel method for a known bottleneck.
The paper tackles the problem of detecting hallucinations in text generated by large language models by introducing KnowHalu, a method that uses multi-form knowledge and step-wise reasoning for factual checking, resulting in improvements of 15.65% in QA tasks and 5.50% in summarization tasks over state-of-the-art baselines.
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 the form of knowledge, KnowHalu proposes a two-phase process for hallucination detection. In the first phase, it identifies non-fabrication hallucinations--responses that, while factually correct, are irrelevant or non-specific to the query. The second phase, multi-form based factual checking, contains five key steps: reasoning and query decomposition, knowledge retrieval, knowledge optimization, judgment generation, and judgment aggregation. Our extensive evaluations demonstrate that KnowHalu significantly outperforms SOTA baselines in detecting hallucinations across diverse tasks, e.g., improving by 15.65% in QA tasks and 5.50% in summarization tasks, highlighting its effectiveness and versatility in detecting hallucinations in LLM-generated content.