解决RAG中检索文档的知识冲突问题，提升生成答案的准确性。
ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation
- 先检测后分类再修复冲突，用轻量模型+大模型精炼降低调用成本。
- 检测准确率达90.8%，冲突识别F1达88.7%，正确率提升5.3%~6.1%。
- 适合需要高可靠性的问答系统，尤其在信息矛盾多的场景下。
检索增强生成（RAG）系统隐含假设检索文档之间知识一致，但实际中常出现矛盾。本文提出ConflictRAG，一种冲突感知的RAG框架，可在生成答案前检测、分类并解决知识冲突。该框架包含三项贡献：（1）两阶段冲突检测模块，结合轻量级嵌入-MLP分类器与选择性LLM精炼，将API调用成本降低62%，同时保持90.8%的检测准确率；（2）基于熵与TOPSIS的数据驱动源可信度评估方法，在选择准确率上比人工规则提升7.1%；（3）冲突感知的RAG评分（CARS），用于诊断冲突处理能力。在三个基准测试中对比六种基线，冲突检测F1达88.7%，相比最强冲突感知基线，正确率持续提升5.3%~6.1%，且在不同主干LLM间具有良好迁移性。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) systems implicitly assume mutual consistency among retrieved documents -- an assumption that frequently fails in practice. We present ConflictRAG, a conflict-aware RAG framework that detects, classifies, and resolves knowledge conflicts prior to answer generation. The framework introduces three contributions: (1) a two-stage conflict detection module combining a lightweight embedding-based MLP classifier with selective LLM refinement, reducing API costs by 62% while maintaining 90.8% detection accuracy; (2) an Entropy-TOPSIS framework for data-driven source credibility assessment, improving selection accuracy by 7.1% over manual heuristics; and (3) a Conflict-Aware RAG Score (CARS) for diagnostic evaluation of conflict-handling capabilities. Experiments on three benchmarks against six baselines demonstrate 88.7% conflict-detection F1 and consistent 5.3--6.1% correctness gains over the strongest conflict-aware baseline, with the pipeline transferring effectively across backbone LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。