如何抓住AI说谎者:通过提出无关问题在黑盒LLM中进行谎言检测
How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
AI总结:
本文提出一种黑盒LLM测谎方法:在疑似谎言后询问无关问题,用是/否回答训练逻辑回归分类器,并证明其可跨架构、微调方式、谄媚及现实销售场景泛化。
摘要:
大型语言模型(LLM)会“说谎”,我们将其定义为尽管在可证明的意义上“知道”真相,却输出虚假陈述。例如,当被指示输出错误信息时,LLM可能会“说谎”。在此,我们开发了一种简单的测谎器,它既不需要访问LLM的激活状态(黑盒),也不需要掌握所涉事实的真值知识。该检测器的工作方式是:在疑似谎言之后提出一组预定义的无关后续问题,并将LLM的是/否答案输入逻辑回归分类器。尽管十分简单,该测谎器却具有很高的准确率,并且具有令人惊讶的通用性。当仅在单一情境的示例上训练——即提示GPT-3.5在事实性问题上说谎——该检测器可分布外泛化至:(1)其他LLM架构,(2)经过微调而说谎的LLM,(3)谄媚性谎言,以及(4)在销售等现实场景中出现的谎言。这些结果表明,LLM具有与谎言相关的独特行为模式,且这些模式在不同架构和语境中保持一致,从而可实现通用型谎言检测。
英文摘要:
Large language models (LLMs) can "lie", which we define as outputting false statements despite "knowing" the truth in a demonstrable sense. LLMs might "lie", for example, when instructed to output misinformation. Here, we develop a simple lie detector that requires neither access to the LLM's activations (black-box) nor ground-truth knowledge of the fact in question. The detector works by asking a predefined set of unrelated follow-up questions after a suspected lie, and feeding the LLM's yes/no answers into a logistic regression classifier. Despite its simplicity, this lie detector is highly accurate and surprisingly general. When trained on examples from a single setting -- prompting GPT-3.5 to lie about factual questions -- the detector generalises out-of-distribution to (1) other LLM architectures, (2) LLMs fine-tuned to lie, (3) sycophantic lies, and (4) lies emerging in real-life scenarios such as sales. These results indicate that LLMs have distinctive lie-related behavioural patterns, consistent across architectures and contexts, which could enable general-purpose lie detection.
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。