通过内部状态分析和聚类可视化和评估大语言模型事实性幻觉倾向
Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clustering
AI总结：
通过FalseCite数据集评估大语言模型在误导性引用下的事实性幻觉倾向，并利用内部状态分析和聚类揭示隐藏状态的特征。
摘要：
大型语言模型（LLMs）经常产生幻觉，生成无意义或虚假信息，这在医学或法律等敏感领域可能尤其有害。为了系统研究这一现象，我们引入了FalseCite，一个经过精心编排的数据集，旨在捕捉并评估由误导性或伪造引用引发的幻觉响应。运行GPT-4o-mini、Falcon-7B和Mistral 7-B通过FalseCite，我们观察到在虚假声明中，尤其是GPT-4o-mini，幻觉活动有显著增加。利用FalseCite的响应，我们也可以分析幻觉模型的内部状态，可视化和聚类隐藏状态向量。从这种分析中，我们注意到无论幻觉与否，隐藏状态向量都倾向于形成一个独特的角形。我们的工作强调了FalseCite作为未来LLM研究评估和缓解幻觉基础的潜力。
英文摘要：
Large Language Models (LLMs) often hallucinate, generating nonsensical or false information that can be especially harmful in sensitive fields such as medicine or law. To study this phenomenon systematically, we introduce FalseCite, a curated dataset designed to capture and benchmark hallucinated responses induced by misleading or fabricated citations. Running GPT-4o-mini, Falcon-7B, and Mistral 7-B through FalseCite, we observed a noticeable increase in hallucination activity for false claims with deceptive citations, especially in GPT-4o-mini. Using the responses from FalseCite, we can also analyze the internal states of hallucinating models, visualizing and clustering the hidden state vectors. From this analysis, we noticed that the hidden state vectors, regardless of hallucination or non-hallucination, tend to trace out a distinct horn-like shape. Our work underscores FalseCite's potential as a foundation for evaluating and mitigating hallucinations in future LLM research.
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。
