效用相关性：基于过程的重写用于RAG
Relevance to Utility: Process-Supervised Rewrite for RAG
AI总结：
R2U通过联合观察重写和回答过程中的推理来近似真实效用，提升检索增强生成系统的生成效用。
摘要：
检索增强生成系统常面临优化检索相关性和生成效用之间的差距。在这种差距下，检索到的文档可能在主题上相关，但仍缺乏生成过程中有效推理所需的内容。尽管现有桥梁模块试图通过重写检索文本来提升生成效果，但我们通过不捕捉“文档效用”来展示其失败。在本工作中，我们提出了R2U，其关键区别在于通过联合观察重写和回答过程中的推理来近似真实的效用。为了蒸馏，R2U将这种监督扩展以增强蒸馏的可靠性。我们进一步构建了效用提升监督，通过测量生成器在重写上下文下的答案增益，获得用于微调和偏好优化的信号。我们评估了我们的方法在多个开放领域问答基准上的表现。实验结果表明，与强大的桥梁基线相比，我们的方法在多个基准上都显示出一致的改进。
英文摘要：
Retrieval-augmented generation systems often suffer from a gap between optimizing retrieval relevance and generative utility. With such a gap, retrieved documents may be topically relevant but still lack the content needed for effective reasoning during generation. While existing bridge modules attempt to rewrite the retrieved text for better generation, we show how they fail by not capturing "document utility". In this work, we propose R2U, with a key distinction of approximating true utility through joint observation of rewriting and answering in the reasoning process. To distill, R2U scale such supervision to enhance reliability in distillation. We further construct utility-improvement supervision by measuring the generator's gain of the answer under the rewritten context, yielding signals for fine-tuning and preference optimization. We evaluate our method across multiple open-domain question-answering benchmarks. The empirical results demonstrate consistent improvements over strong bridging baselines
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
