AuthorityBench: Benchmarking LLM Authority Perception for Reliable Retrieval-Augmented Generation
This addresses the issue of misinformation propagation in RAG systems for users relying on LLMs for reliable knowledge retrieval, though it is incremental as it focuses on benchmarking rather than proposing a new method.
The paper tackles the problem of LLMs being vulnerable to low-authority sources in Retrieval-Augmented Generation (RAG) by introducing AuthorityBench, a benchmark to evaluate LLM authority perception, and finds that authority-guided filtering improves answer accuracy in downstream RAG experiments.
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) with external knowledge but remains vulnerable to low-authority sources that can propagate misinformation. We investigate whether LLMs can perceive information authority - a capability extending beyond semantic understanding. To address this, we introduce AuthorityBench, a comprehensive benchmark for evaluating LLM authority perception comprising three datasets: DomainAuth (10K web domains with PageRank-based authority), EntityAuth (22K entities with popularity-based authority), and RAGAuth (120 queries with documents of varying authority for downstream evaluation). We evaluate five LLMs using three judging methods (PointJudge, PairJudge, ListJudge) across multiple output formats. Results show that ListJudge and PairJudge with PointScore output achieve the strongest correlation with ground-truth authority, while ListJudge offers optimal cost-effectiveness. Notably, incorporating webpage text consistently degrades judgment performance, suggesting authority is distinct from textual style. Downstream experiments on RAG demonstrate that authority-guided filtering largely improves answer accuracy, validating the practical importance of authority perception for reliable knowledge retrieval. Code and benchmark are available at: https://github.com/Trustworthy-Information-Access/AuthorityBench.