Retrieval-augmented generation (RAG) grounds large language models with external evidence, but under a limited context budget, the key challenge is deciding which retrieved passages should be injected. We show that retrieval relevance metrics (e.g., NDCG) correlate weakly with end-to-end QA quality and can even become negatively correlated under multi-passage injection, where redundancy and mild conflicts destabilize generation. We propose \textbf{Information Gain Pruning (IGP)}, a deployment-friendly reranking-and-pruning module that selects evidence using a generator-aligned utility signal and filters weak or harmful passages before truncation, without changing existing budget interfaces. Across five open-domain QA benchmarks and multiple retrievers and generators, IGP consistently improves the quality--cost trade-off. In a representative multi-evidence setting, IGP delivers about +12--20% relative improvement in average F1 while reducing final-stage input tokens by roughly 76--79% compared to retriever-only baselines.
@article{arxiv.2601.17532,
title = {Less is More for RAG: Information Gain Pruning for Generator-Aligned Reranking and Evidence Selection},
author = {Zhipeng Song and Yizhi Zhou and Xiangyu Kong and Jiulong Jiao and Xinrui Bao and Xu You and Xueqing Shi and Yuhang Zhou and Heng Qi},
journal= {arXiv preprint arXiv:2601.17532},
year = {2026}
}