Automatic Evaluation of Attribution by Large Language Models
Xiang Yue Boshi Wang Ziru Chen Kai Zhang Yu Su Huan Sun The Ohio State University
Abstract
A recent focus of large language model (LLM) development, as exemplified by generative search engines, is to incorporate external references to generate and support its claims. However, evaluating the attribution, i.e., verifying whether the generated statement is fully supported by the cited reference, remains an open problem. Although human evaluation is common practice, it is costly and time-consuming. In this paper, we investigate automatic evaluation of attribution given by LLMs. We begin by defining different types of attribution errors, and then explore two approaches for automatic evaluation: prompting LLMs and fine-tuning smaller LMs. The fine-tuning data is repurposed from related tasks such as question answering, fact-checking, natural language inference, and summarization. We manually curate a set of test examples covering 12 domains from a generative search engine, New Bing. Our results on this curated test set and simulated examples from existing benchmarks highlight both promising signals and challenges. We hope our problem formulation, testbeds, and findings will help lay the foundation for future studies on this important problem.111Our code and dataset are availab
中文速览
大型语言模型（LLM）在生成内容时往往会引用外部参考文献，但这些引用是否真正支撑了所生成的内容——即"归因"（attribution）是否准确——至今仍是一个难题，靠人工核查既昂贵又低效。为此，本文提出了 AttrScore 框架，将归因错误细分为三类：可归因（reference 完全支持生成内容）、外推型错误（reference 信息不足以验证生成内容）和矛盾型错误（生成内容与 reference 直接冲突），并探索了两种自动评估方法——直接提示 ChatGPT 等大模型，以及在问答、事实核查、自然语言推理和文本摘要等相关任务数据上微调较小的语言模型。研究者还手工整理了一个覆盖 12 个领域、来自生成式搜索引擎 New Bing 的真实测试集（AttrEval-GenSearch），实验结果表明两种方法均有一定效果，但在细粒度数值比较、逻辑推理等方面仍有明显短板。这项工作为自动化评估 LLM 归因准确性这一重要问题提供了问题定义、数据集和基准，有助于推动更可信、更安全的生成式搜索系统的研究。
原文 arXiv:2305.06311;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2305.06311v2