用于减少大语言模型无依据幻觉的自然语言推理链
Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations
AI总结：
针对大语言模型易生成无依据幻觉的问题，提出基于自然语言推理链的即插即用分层框架，无需微调或领域提示工程，通过后编辑减幻，在多场景下实现检测与减幻的优异性能。
摘要：
大语言模型（LLMs）在获得相关文档作为背景上下文时能够生成流畅的自然语言文本，这一能力引发了业界对开发LLMs应用的浓厚兴趣。然而，LLMs容易生成无法由所提供来源支撑的幻觉内容。本文提出一种分层框架来检测并缓解此类无依据幻觉。该框架采用自然语言推理链（Chain of Natural Language Inference, CoNLI）进行幻觉检测，并通过后编辑减少幻觉。我们的方法无需任何微调或特定领域的提示工程，仅使用LLMs就在幻觉检测上达到了当前最优性能，还通过重写提升了文本质量。研究表明，这个简单的即插即用框架可作为幻觉检测与消减的有效方案，在多种上下文场景中均能取得有竞争力的表现。
英文摘要：
Large language models (LLMs) can generate fluent natural language texts when given relevant documents as background context. This ability has attracted considerable interest in developing industry applications of LLMs. However, LLMs are prone to generate hallucinations that are not supported by the provided sources. In this paper, we propose a hierarchical framework to detect and mitigate such ungrounded hallucination. Our framework uses Chain of Natural Language Inference (CoNLI) for hallucination detection and hallucination reduction via post-editing. Our approach achieves state-of-the-art performance on hallucination detection and enhances text quality through rewrite, using LLMs without any fine-tuning or domain-specific prompt engineering. We show that this simple plug-and-play framework can serve as an effective choice for hallucination detection and reduction, achieving competitive performance across various contexts.
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。
