用可解释的选段代替传统重排序，提升敏感领域RAG的可信与安全
Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains
- 通过生成显式理由的LLM和自适应截断机制实现可解释选段
- 召回率提升13.41%，精度提高21.05%，证据量减少80%
- 适合对可解释性、抗攻击性要求高的医疗、金融等敏感场景
部署在敏感领域的检索增强生成（RAG）系统需提供可解释的证据选择和对抗数据投毒的鲁棒保障，但现有方法依赖不透明的相似度检索与任意top-k截断，既无法解释选择依据，又易受恶意干扰。METEORA将重排序替换为基于理由的选段机制：采用DPO微调的LLM生成明确检索理由，证据片段选择引擎（ECSE）结合统计肘部检测动态确定截断点，验证器LLM则利用相同理由过滤被污染的证据。在六个数据集上，METEORA实现13.41%的召回率提升、21.05%的精度提升（无扩展）、证据体积减少80%、答案准确率提升33.34%、对抗鲁棒性提高4.4倍。人工评估显示解释性可信度达3.64/5，真实答案匹配率达86%，证明可解释性、效率与鲁棒性可协同提升。代码已开源。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) systems deployed in sensitive domains must provide interpretable evidence selection and robust safeguards against data poisoning, yet current approaches rely on opaque similarity-based retrieval with arbitrary top-k cutoffs that offer no explanation for their selections and remain vulnerable to adversarial manipulation. METEORA replaces re-ranking with rationale-driven selection via three components: a DPO-tuned LLM that generates explicit retrieval rationales, an Evidence Chunk Selection Engine (ECSE) that uses those rationales with statistical elbow detection for adaptive cutoff determination, and a Verifier LLM that filters poisoned evidence using the same rationales. Across six datasets, METEORA achieves 13.41% higher recall, 21.05% higher precision (without expansion), an 80% reduction in evidence volume, a 33.34% improvement in answer accuracy, and a 4.4x improvement in adversarial robustness. Human evaluation confirms genuine interpretability (3.64/5 confidence; 86% ground-truth agreement), demonstrating that interpretability, efficiency, and robustness are synergistic rather than competing objectives. The code is available in the GitHub repository https://github.com/YashSaxena21/METEORA
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。