Relevance to Utility: Process-Supervised Rewrite for RAG

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 this observation reliably, R2U scales the process to isolate individual rewrites.We further construct utility-improvement supervision by measuring the generator's gain of the answer under the rewritten context, yielding signals for finetuning and preference optimization.We evaluate our method across multiple open-domain question-answering benchmarks.The empirical results demonstrate consistent improvements over strong bridging baselines.1