发现幻觉首词比后续幻觉词更易检测，对精准定位幻觉有重要启示。
First Hallucination Tokens Are Different from Conditional Ones
- 基于RAGTruth语料的细粒度标注，分析幻觉词分布模式。
- 首幻觉词检测准确率显著高于后续幻觉词，跨模型保持一致。
- 为幻觉检测提供新思路，适合关注模型可信性的研究者。
大语言模型会产生幻觉，检测这些情况对确保信任至关重要。尽管已有方法在响应或片段层面处理幻觉检测，近期工作探索了词元级别的检测，实现更精细干预。然而，幻觉信号在幻觉词序列中的分布尚未被研究。我们利用RAGTruth语料的词元级标注，发现首个幻觉词远比后续幻觉词更易检测。这一结构特性在多个模型中均成立，表明首幻觉词在词元级幻觉检测中起关键作用。代码已公开于https://github.com/jakobsnl/RAGTruth_Xtended。
原文摘要 · Abstract (English)
Large Language Models (LLMs) hallucinate, and detecting these cases is key to ensuring trust. While many approaches address hallucination detection at the response or span level, recent work explores token-level detection, enabling more fine-grained intervention. However, the distribution of hallucination signal across sequences of hallucinated tokens remains unexplored. We leverage token-level annotations from the RAGTruth corpus and find that the first hallucinated token is far more detectable than later ones. This structural property holds across models, suggesting that first hallucination tokens play a key role in token-level hallucination detection. Our code is available at https://github.com/jakobsnl/RAGTruth_Xtended.
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。