KnowHalu：基于多形式知识事实核查的幻觉检测
KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking
AI总结：
本文提出 KnowHalu，通过两阶段流程、多形式知识事实核查与判断聚合检测 LLM 幻觉，在 QA 和摘要任务上分别较 SOTA 提升 15.65% 与 5.50%。
摘要：
本文介绍了 KnowHalu，这是一种用于检测大型语言模型（LLM）生成文本中幻觉的新颖方法，利用逐步推理、多形式化查询、用于事实核查的多形式知识以及基于融合的检测机制。随着 LLM 越来越多地应用于各个领域，确保其输出不产生幻觉至关重要。现有方法要么依赖 LLM 的自一致性检查，要么进行事后事实核查，而没有考虑查询的复杂性或知识形式；在认识到这些局限性后，KnowHalu 提出了一个两阶段的幻觉检测流程。第一阶段识别非捏造型幻觉——那些虽然事实上正确，但与查询无关或不具体的回答。第二阶段是基于多形式的事实核查，包含五个关键步骤：推理与查询分解、知识检索、知识优化、判断生成和判断聚合。大量评估表明，KnowHalu 在多种任务上的幻觉检测表现显著优于 SOTA 基线，例如在 QA 任务上提升 15.65%，在摘要任务上提升 5.50%，突显了其在检测 LLM 生成内容中幻觉方面的有效性和通用性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
