ConflictBank：用于评估LLM中知识冲突影响的基准。

ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM

August 22, 2024

作者: Zhaochen Su, Jun Zhang, Xiaoye Qu, Tong Zhu, Yanshu Li, Jiashuo Sun, Juntao Li, Min Zhang, Yu Cheng

cs.AI

摘要

大型语言模型（LLMs）在许多学科取得了令人瞩目的进展，然而知识冲突这一重要问题，作为幻觉的主要来源，却鲜有研究。只有少数研究探讨了LLMs固有知识与检索到的上下文知识之间的冲突。然而，对LLMs中知识冲突的彻底评估仍然缺失。受到这一研究空白的启发，我们提出ConflictBank，这是第一个全面的基准，旨在系统评估三个方面的知识冲突：（i）检索到的知识中遇到的冲突，（ii）模型编码知识内部的冲突，以及（iii）这些冲突形式之间的相互作用。我们的调查深入研究了四个模型系列和十二个LLM实例，精心分析了由错误信息、时间差异和语义分歧引起的冲突。基于我们提出的新颖构建框架，我们创建了7,453,853个主张-证据对和553,117个问答对。我们提出了关于模型规模、冲突原因和冲突类型的许多发现。我们希望我们的ConflictBank基准能够帮助社区更好地理解模型在冲突中的行为，并开发更可靠的LLMs。

English

Large language models (LLMs) have achieved impressive advancements across numerous disciplines, yet the critical issue of knowledge conflicts, a major source of hallucinations, has rarely been studied. Only a few research explored the conflicts between the inherent knowledge of LLMs and the retrieved contextual knowledge. However, a thorough assessment of knowledge conflict in LLMs is still missing. Motivated by this research gap, we present ConflictBank, the first comprehensive benchmark developed to systematically evaluate knowledge conflicts from three aspects: (i) conflicts encountered in retrieved knowledge, (ii) conflicts within the models' encoded knowledge, and (iii) the interplay between these conflict forms. Our investigation delves into four model families and twelve LLM instances, meticulously analyzing conflicts stemming from misinformation, temporal discrepancies, and semantic divergences. Based on our proposed novel construction framework, we create 7,453,853 claim-evidence pairs and 553,117 QA pairs. We present numerous findings on model scale, conflict causes, and conflict types. We hope our ConflictBank benchmark will help the community better understand model behavior in conflicts and develop more reliable LLMs.