提示引导的内部状态用于大型语言模型的幻觉检测
Prompt-Guided Internal States for Hallucination Detection of Large Language Models
AI总结：
本文提出PRISM框架，利用提示引导LLM内部状态中与真实性相关的结构变化，仅用域内数据增强幻觉检测器的跨域泛化能力，实验验证其显著提升现有方法的跨域性能。
摘要：
大型语言模型（LLMs）在不同领域的各种任务中展现出了卓越的能力。然而，它们有时会生成逻辑连贯但事实错误或具有误导性的响应，这被称为LLM幻觉。数据驱动的监督方法通过利用LLMs的内部状态来训练幻觉检测器，但在特定领域训练的检测器往往难以很好地泛化到其他领域。在本文中，我们旨在仅使用域内数据来增强监督检测器的跨域性能。我们提出了一种新颖的框架，即提示引导的内部状态用于LLM幻觉检测，简称PRISM。通过利用适当的提示来引导LLMs内部状态中与文本真实性相关的结构发生变化，我们使这种结构在不同领域的文本中更加显著和一致。我们将我们的框架与现有的幻觉检测方法集成，并在不同领域的数据集上进行了实验。实验结果表明，我们的框架显著增强了现有幻觉检测方法的跨域泛化能力。
英文摘要：
Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of tasks in different domains. However, they sometimes generate responses that are logically coherent but factually incorrect or misleading, which is known as LLM hallucinations. Data-driven supervised methods train hallucination detectors by leveraging the internal states of LLMs, but detectors trained on specific domains often struggle to generalize well to other domains. In this paper, we aim to enhance the cross-domain performance of supervised detectors with only in-domain data. We propose a novel framework, prompt-guided internal states for hallucination detection of LLMs, namely PRISM. By utilizing appropriate prompts to guide changes to the structure related to text truthfulness in LLMs' internal states, we make this structure more salient and consistent across texts from different domains. We integrated our framework with existing hallucination detection methods and conducted experiments on datasets from different domains. The experimental results indicate that our framework significantly enhances the cross-domain generalization of existing hallucination detection methods.
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。
