Tag
This paper introduces MediaRef, a publicly available knowledge store of web-sourced documents for reproducible, low-cost evaluation of media background check generation using LLMs, addressing the limitation of costly proprietary APIs.
ConflictRAG is a conflict-aware RAG framework that detects, classifies, and resolves knowledge conflicts in retrieved documents, achieving 88.7% detection F1 and 5.3–6.1% correctness gains over baselines while reducing API costs by 62%.
This paper investigates how LLMs handle knowledge conflicts in retrieval-augmented generation by studying their preferences for different information sources. The authors find that LLMs prefer institutionally-corroborated sources but these preferences can be reversed by repetition, proposing a method to reduce repetition bias while maintaining consistent source preferences.