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

TL;DR

ConflictBank is a comprehensive benchmark designed to evaluate knowledge conflicts in large language models, addressing a critical source of hallucinations by analyzing conflicts in retrieved and encoded knowledge across multiple models.

Contribution

This paper introduces ConflictBank, the first large-scale benchmark for systematically assessing knowledge conflicts in LLMs from various aspects and sources.

Findings

Identified key conflict types and causes in LLMs

Analyzed conflict patterns across different model scales

Created over 7 million claim-evidence pairs for evaluation

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.