HALoGEN：神奇的大语言模型幻觉及其分布位置
HALoGEN: Fantastic LLM Hallucinations and Where to Find Them
AI总结：
本研究发布综合性幻觉基准HALoGEN，含9领域10923条提示与自动核验器，评估14个模型的15万条生成内容，发现最优模型幻觉占比最高达86%，还提出三类幻觉错误分类，助力可信LLM研发。
摘要：
尽管生成式大语言模型（LLM）在生成高质量流畅文本方面能力出众，但它们也会产生幻觉——即与既定世界知识或给定输入上下文不符的表述。然而，衡量幻觉现象颇具挑战，因为让人类实时核验模型生成内容既昂贵又耗时。\n本研究发布了HALoGEN，这是一个综合性幻觉基准，包含两部分：（1）面向生成式模型的10923条提示词，覆盖编程、科学归因、摘要生成等9个领域；（2）针对每个用例的高精度自动核验器，可将LLM生成内容拆解为原子单元，并对照高质量知识源核验每个单元。\n我们利用该框架评估了来自14个语言模型的约15万条生成内容，发现即便是性能最优的模型也充斥着幻觉——根据领域不同，生成的原子事实中幻觉占比有时高达86%。我们进一步提出了一种全新的LLM幻觉错误分类体系，依据幻觉的可能来源划分：源自训练数据回忆错误的为A型错误，源自训练数据中错误知识的为B型错误，属于凭空捏造的为C型错误。我们希望该框架能为系统研究生成式模型产生幻觉的原因奠定基础，并推动可信大语言模型的研发。
英文摘要：
Despite their impressive ability to generate high-quality and fluent text, generative large language models (LLMs) also produce hallucinations: statements that are misaligned with established world knowledge or provided input context. However, measuring hallucination can be challenging, as having humans verify model generations on-the-fly is both expensive and time-consuming. In this work, we release HALoGEN, a comprehensive hallucination benchmark consisting of: (1) 10,923 prompts for generative models spanning nine domains including programming, scientific attribution, and summarization, and (2) automatic high-precision verifiers for each use case that decompose LLM generations into atomic units, and verify each unit against a high-quality knowledge source. We use this framework to evaluate ~150,000 generations from 14 language models, finding that even the best-performing models are riddled with hallucinations (sometimes up to 86% of generated atomic facts depending on the domain). We further define a novel error classification for LLM hallucinations based on whether they likely stem from incorrect recollection of training data (Type A errors), or incorrect knowledge in training data (Type B errors), or are fabrication (Type C errors). We hope our framework provides a foundation to enable the principled study of why generative models hallucinate, and advances the development of trustworthy large language models.
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。
