面向语言模型的细粒度幻觉检测与编辑
Fine-grained Hallucination Detection and Editing for Language Models
AI总结：
该研究提出大语言模型细粒度幻觉分类体系与自动检测任务，构建含千条标注的FavaBench基准，训练检索增强模型FAVA，其检测性能优于ChatGPT和GPT-4，且编辑建议可提升生成文本事实性。
摘要：
大语言模型（LM）容易生成事实性错误，这类错误通常被称为幻觉。本文提出了一套全面的幻觉分类体系，并指出幻觉存在多种表现形式，每种形式的事实性核查需要不同程度的细致评估。我们提出了自动细粒度幻觉检测这一新型任务，并构建了新的评估基准FavaBench，该基准包含跨多个领域、针对3个语言模型输出的约1000条细粒度人工标注判断。分析显示，在信息查询场景下，ChatGPT和Llama2-Chat（70B、7B）的多数输出中存在多种类型的幻觉。我们通过精心构建合成数据，训练了检索增强型语言模型FAVA，用于检测和修正细粒度幻觉。在我们的基准上，自动评估与人工评估均表明，FAVA在细粒度幻觉检测任务上显著优于ChatGPT和GPT-4，且FAVA给出的编辑建议可提升语言模型生成文本的事实准确性。
英文摘要：
Large language models (LMs) are prone to generate factual errors, which are often called hallucinations. In this paper, we introduce a comprehensive taxonomy of hallucinations and argue that hallucinations manifest in diverse forms, each requiring varying degrees of careful assessments to verify factuality. We propose a novel task of automatic fine-grained hallucination detection and construct a new evaluation benchmark, FavaBench, that includes about one thousand fine-grained human judgments on three LM outputs across various domains. Our analysis reveals that ChatGPT and Llama2-Chat (70B, 7B) exhibit diverse types of hallucinations in the majority of their outputs in information-seeking scenarios. We train FAVA, a retrieval-augmented LM by carefully creating synthetic data to detect and correct fine-grained hallucinations. On our benchmark, our automatic and human evaluations show that FAVA significantly outperforms ChatGPT and GPT-4 on fine-grained hallucination detection, and edits suggested by FAVA improve the factuality of LM-generated text.
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。
