用轻量级重排序提升RAG生成质量，直接优化文档顺序。
LURE-RAG: Lightweight Utility-driven Reranking for Efficient RAG
- 基于LambdaMART的轻量重排序器，结合大模型评估的实用性。
- 在两个数据集上达到基线97%-98%性能，训练推理更高效。
- 适合追求高效且高质量RAG系统的研发人员使用。
现有检索增强生成（RAG）系统多依赖相关性检索，但与实际生成效果的实用价值常不一致。现有实用驱动型检索方法存在资源消耗高、训练中缺乏列表级排序损失两大缺陷，后者尤为关键，因文档顺序直接影响生成结果。为此，本文提出轻量级实用驱动重排序框架LURE-RAG，可为任意黑盒检索器添加高效的基于LambdaMART的重排序模块。该方法通过大模型评估的实用价值引导列表级排序损失进行训练，直接优化检索文档的相对顺序。在两个标准数据集上的实验表明，LURE-RAG性能达最先进的密集神经基线的97%-98%，同时保持训练与推理效率。其密集版本UR-RAG更较最优现有基线提升最高3%。
原文摘要 · Abstract (English)
Most conventional Retrieval-Augmented Generation (RAG) pipelines rely on relevance-based retrieval, which often misaligns with utility -- that is, whether the retrieved passages actually improve the quality of the generated text specific to a downstream task such as question answering or query-based summarization. The limitations of existing utility-driven retrieval approaches for RAG are that, firstly, they are resource-intensive typically requiring query encoding, and that secondly, they do not involve listwise ranking loss during training. The latter limitation is particularly critical, as the relative order between documents directly affects generation in RAG. To address this gap, we propose Lightweight Utility-driven Reranking for Efficient RAG (LURE-RAG), a framework that augments any black-box retriever with an efficient LambdaMART-based reranker. Unlike prior methods, LURE-RAG trains the reranker with a listwise ranking loss guided by LLM utility, thereby directly optimizing the ordering of retrieved documents. Experiments on two standard datasets demonstrate that LURE-RAG achieves competitive performance, reaching 97-98% of the state-of-the-art dense neural baseline, while remaining efficient in both training and inference. Moreover, its dense variant, UR-RAG, significantly outperforms the best existing baseline by up to 3%.
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。