让大模型在干扰信息中更准答问题，提升事实准确性。
PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning
- 用真假混杂的题目训练模型，增强抗干扰能力
- 在12个基准上平均事实准确率提升5.4%
- 无需复杂人工指令，适合实际应用部署
检索增强生成（RAG）在面对混淆性半相关文本或需深度推理时表现不佳。本文提出高效微调框架PrismRAG，通过两种方式提升性能：（i）使用包含真实证据与细微干扰项的问答对进行训练；（ii）引导大模型自主规划、推理和整合，减少对人工指令的依赖。在涵盖多个应用场景的12个开放书RAG问答基准上评估，PrismRAG平均事实准确率提升5.4%，优于现有最优方案。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) often falls short when retrieved context includes confusing semi-relevant passages, or when answering questions require deep contextual understanding and reasoning. We propose an efficient fine-tuning framework, called PrismRAG, that (i) trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages, and (ii) instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without relying on extensive human engineered instructions. Evaluated across 12 open-book RAG QA benchmarks spanning diverse application domains and scenarios, PrismRAG improves average factuality by 5.4%, outperforming state-of-the-art solutions.
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。