提出轻量诊断修复框架，提升RAG在资源受限下的事实准确性
Diagnosing and Repairing Factual Errors in RAG under Budget Constraints
- 通过查询、检索内容和生成结果的可观测信号诊断错误类型
- 在延迟和显存约束下选择最优修复操作，准确率提升12.3%（FEVER）
- 无需微调或内部模型信号，适合黑盒部署场景
检索增强生成（RAG）通过外部证据提升大模型的事实性，但实际部署中仍易出错。问题常源于证据缺失或相关性弱，以及生成内容未能忠实反映检索信息。现有方法多依赖微调、内部信号访问或不计资源的升级策略，在黑盒和资源受限场景中难以应用。本文提出D2R-RAG（诊断-修复RAG），一种模型无关且资源感知的框架，结合轻量级故障诊断与自适应修复。该框架从查询、检索证据和生成响应的可观测信号中提取可解释的故障特征，并在明确的延迟与显存约束下，从少量纠正动作中选择最优方案。在FEVER和HotpotQA数据集上的实验表明，D2R-RAG优于近期基线，且在多种计算预算下实现更优的准确率-效率权衡。代码已开源。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) improves the factuality of large language models by grounding responses in external evidence, yet real-world deployments remain fragile. Failures often stem from missing or weakly relevant evidence, as well as from generation that does not faithfully reflect the retrieved context. Many existing approaches rely on fine-tuning, privileged access to internal model signals, or resource-insensitive escalation strategies, which limits their practicality in black-box and budget-constrained settings. We propose D2R-RAG (Diagnose-to-Repair RAG), a model-agnostic and resource-aware framework that combines lightweight failure diagnosis with adaptive repair. D2R-RAG derives interpretable failure signatures from observable signals in the query, retrieved evidence, and generated response, and then selects from a small set of corrective actions under explicit latency and VRAM constraints. Experiments on FEVER and HotpotQA show that D2R-RAG improves reliability over recent baselines and achieves better accuracy--efficiency trade-offs across multiple compute budgets. The code is available at https://github.com/CyberScienceLab/D2R-RAG/.
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。