探索 LLM 真相方向在对话格式上的泛化性
Exploring the generalization of LLM truth directions on conversational formats
AI总结：
本文研究 LLM 真相方向在不同对话格式间的泛化问题，发现短对话表现良好而长提示中前置谎言难以泛化，并通过末尾固定关键短语显著提升检测效果。
摘要：
近期多项研究认为，LLM 具有一个通用的真相方向：在模型的激活空间中，真陈述与假陈述是线性可分的。已有研究表明，在模型的单个隐藏状态上训练的线性探针已经能够泛化到一系列主题，甚至可能用于 LLM 对话中的谎言检测。在本研究中，我们探索这一真相方向如何在不同对话格式之间泛化。我们发现，在以谎言结尾的短对话之间具有良好的泛化性，但对于谎言出现在输入提示较前位置的较长格式，泛化性较差。我们提出一种解决方案，通过在每段对话末尾添加一个固定关键短语，显著改善此类泛化。我们的结果凸显了构建可泛化到新场景的可靠 LLM 谎言检测器所面临的挑战。
英文摘要：
Several recent works argue that LLMs have a universal truth direction where true and false statements are linearly separable in the activation space of the model. It has been demonstrated that linear probes trained on a single hidden state of the model already generalize across a range of topics and might even be used for lie detection in LLM conversations. In this work we explore how this truth direction generalizes between various conversational formats. We find good generalization between short conversations that end on a lie, but poor generalization to longer formats where the lie appears earlier in the input prompt. We propose a solution that significantly improves this type of generalization by adding a fixed key phrase at the end of each conversation. Our results highlight the challenges towards reliable LLM lie detectors that generalize to new settings.
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。
