Paper · arXiv 2408.12076
ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM
Zhaochen Su, Jun Zhang, Xiaoye Qu, Tong Zhu, Yanshu Li, Jiashuo Sun, Juntao Li, Min Zhang, Yu Cheng
ConflictBank is a benchmark for evaluating knowledge conflicts in LLMs by assessing retrieved knowledge, model-encoded knowledge, and their interplay across different model families and causes like misinformation and temporal discrepancies.
Abstract
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.