让大模型自己识别幻觉，用思维链方法提升检测率。
Can LLMs Detect Their Own Hallucinations?
- 用思维链提取模型参数中的知识，做幻觉分类
- GPT-3.5 Turbo用此法检出自身58.2%的幻觉
- 适合关注模型自检能力的研究者
大型语言模型（LLMs）虽能生成流畅回答，但常产生事实性幻觉。本文探究模型能否识别自身幻觉，将幻觉检测建模为句子分类任务。提出一种评估框架及基于思维链（CoT）的知识提取分类方法。实验表明，使用思维链的GPT-3.5 Turbo可检测出58.2%的自身幻觉，证明当参数中包含足够知识时，大模型具备自我检测幻觉的能力。
原文摘要 · Abstract (English)
Large language models (LLMs) can generate fluent responses, but sometimes hallucinate facts. In this paper, we investigate whether LLMs can detect their own hallucinations. We formulate hallucination detection as a classification task of a sentence. We propose a framework for estimating LLMs' capability of hallucination detection and a classification method using Chain-of-Thought (CoT) to extract knowledge from their parameters. The experimental results indicated that GPT-$3.5$ Turbo with CoT detected $58.2\%$ of its own hallucinations. We concluded that LLMs with CoT can detect hallucinations if sufficient knowledge is contained in their parameters.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。