让大模型与检索器协同优化，生成更适配的查询扩展。
ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance
- 大模型生成语义丰富扩展查询，联合训练提升检索能力。
- 在多个基准上提升超5%，显著优于现有方法。
- 适合需要高质量文本检索的研究者和开发者。
大型语言模型（LLMs）在通过查询增强提升密集检索方面展现出巨大潜力。然而，现有方法通常将大模型与检索器视为独立模块，忽略了生成与排序目标之间的对齐。本文提出 ExpandR，一种统一的大模型增强密集检索框架，联合优化大模型与检索器。ExpandR 利用大模型生成语义丰富的查询扩展，并用于增强检索器训练；同时，大模型通过直接偏好优化（DPO）进行训练，由精心设计的奖励函数引导，平衡检索效果与生成一致性。该联合优化范式实现大模型与检索器的相互适应，生成既信息丰富又适配检索的查询扩展。在多个基准上的实验结果表明，ExpandR 持续优于强基线，在检索性能上提升超过 5%。代码已开源：https://github.com/NEUIR/ExpandR。
原文摘要 · Abstract (English)
Large language models (LLMs) have demonstrated significant potential in enhancing dense retrieval through query augmentation. However, most existing methods treat the LLM and the retriever as separate modules, overlooking the alignment between generation and ranking objectives. In this work, we propose ExpandR, a unified LLM-augmented dense retrieval framework that jointly optimizes both the LLM and the retriever. ExpandR employs the LLM to generate semantically rich query expansions, which are leveraged to enhance the retriever's training. Simultaneously, the LLM is trained using Direct Preference Optimization (DPO), guided by a carefully designed reward function that balances retrieval effectiveness and generation consistency. This joint optimization paradigm enables mutual adaptation between the LLM and the retriever, resulting in query expansions that are both informative and well-suited for retrieval. Experimental results on multiple benchmarks show that ExpandR consistently outperforms strong baselines, achieving more than a 5% improvement in retrieval performance. All codes are available at https://github.com/NEUIR/ExpandR.
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。