提出反馈适应新评估框架，衡量RAG系统纠错速度与效果。
Feedback Adaptation for Retrieval-Augmented Generation
- 引入纠正延迟与反馈后性能双维度评估
- 训练方法存在纠错延迟与可靠性的权衡
- PatchRAG实现无需重训的即时纠错与泛化
检索增强生成（RAG）系统通常在静态假设下评估，但实际部署中常通过用户或专家反馈进行修正。现有评估协议侧重整体准确率，未能捕捉反馈引入后的系统适应行为。本文提出反馈适应问题设置，关注纠错反馈在后续查询中的传播效率与速度。为此，我们设计两个评估维度：纠正延迟（反馈提供与行为改变之间的时延）和反馈后性能（对语义相关查询的可靠性）。实验表明，基于训练的方法在纠错延迟与可靠适应间存在权衡。我们进一步提出PatchRAG，一种仅需推理时修改的轻量级方案，无需重新训练即可实现即时纠正，并在新查询上表现出强泛化能力。结果表明，反馈适应是交互式RAG系统中被忽视的重要行为维度。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) systems are typically evaluated under static assumptions, despite being frequently corrected through user or expert feedback in deployment. Existing evaluation protocols focus on overall accuracy and fail to capture how systems adapt after feedback is introduced. We introduce feedback adaptation as a problem setting for RAG systems, which asks how effectively and how quickly corrective feedback propagates to future queries. To make this behavior measurable, we propose two evaluation axes: correction lag, which captures the delay between feedback provision and behavioral change, and post-feedback performance, which measures reliability on semantically related queries after feedback. Using these metrics, we show that training-based approaches exhibit a trade-off between delayed correction and reliable adaptation. We further propose PatchRAG, a minimal inference-time instantiation that incorporates feedback without retraining, demonstrating immediate correction and strong post-feedback generalization under the proposed evaluation. Our results highlight feedback adaptation as a previously overlooked dimension of RAG system behavior in interactive settings.
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。