HaloScope：利用无标签LLM生成内容进行幻觉检测
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
AI总结：
本文提出HaloScope框架，利用无标签LLM生成内容，通过自动成员估计分数区分真实与幻觉信息并训练分类器，无需额外标注即实现卓越的幻觉检测性能。
摘要：
大型语言模型（LLM）应用的激增引发了人们对生成误导性或捏造信息（即幻觉）的担忧。因此，检测幻觉已成为维护对LLM生成内容信任的关键。学习真实性分类器的一个主要挑战是缺乏大量带标签的真实和幻觉数据。为了解决这一挑战，我们引入了HaloScope，这是一种新颖的学习框架，利用自然环境中无标签的LLM生成内容进行幻觉检测。这种无标签数据在开放世界中部署LLM时自由产生，并包含真实和幻觉信息。为了利用这些无标签数据，我们提出了一种自动化的成员估计分数，用于区分无标签混合数据中的真实和不真实生成内容，从而能够在其基础上训练二元真实性分类器。重要的是，我们的框架不需要额外的数据收集和人工注释，为实际应用提供了强大的灵活性和实用性。大量实验表明，HaloScope能够实现卓越的幻觉检测性能，以显著优势超越了有竞争力的对手。代码可在https://github.com/deeplearningwisc/haloscope获取。
英文摘要：
The surge in applications of large language models (LLMs) has prompted concerns about the generation of misleading or fabricated information, known as hallucinations. Therefore, detecting hallucinations has become critical to maintaining trust in LLM-generated content. A primary challenge in learning a truthfulness classifier is the lack of a large amount of labeled truthful and hallucinated data. To address the challenge, we introduce HaloScope, a novel learning framework that leverages the unlabeled LLM generations in the wild for hallucination detection. Such unlabeled data arises freely upon deploying LLMs in the open world, and consists of both truthful and hallucinated information. To harness the unlabeled data, we present an automated membership estimation score for distinguishing between truthful and untruthful generations within unlabeled mixture data, thereby enabling the training of a binary truthfulness classifier on top. Importantly, our framework does not require extra data collection and human annotations, offering strong flexibility and practicality for real-world applications. Extensive experiments show that HaloScope can achieve superior hallucination detection performance, outperforming the competitive rivals by a significant margin. Code is available at https://github.com/deeplearningwisc/haloscope.
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。
