用大模型优化查询分解，提升多向量检索效果
POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval
- 用大模型生成提示词自动优化查询拆分策略
- 在RAG问答任务中检索准确率和端到端正确率均更优
- 可无缝集成到各类检索增强系统，训练成本可控
尽管多向量检索（MVR）在众多信息检索任务中已达到领先水平，其性能高度依赖于查询的分解方式（如短语或词元）。然而，针对MVR性能优化查询分解并非端到端可微，且与下游检索系统（如RAG）联合训练效率低下。为此，我们提出性能导向查询分解器（POQD），利用一个大模型进行查询分解，并通过另一个大模型优化提示词以搜索最优分解方案。我们进一步设计了端到端交替优化算法，同步优化提示词与下游模型。理论分析表明该方法可在合理训练成本下实现优越的MVR性能。实验在典型的RAG问答任务上验证，POQD在检索性能和端到端问答准确率上均优于现有策略。代码已开源：https://github.com/PKU-SDS-lab/POQD-ICML25。
原文摘要 · Abstract (English)
Although Multi-Vector Retrieval (MVR) has achieved the state of the art on many information retrieval (IR) tasks, its performance highly depends on how to decompose queries into smaller pieces, say phrases or tokens. However, optimizing query decomposition for MVR performance is not end-to-end differentiable. Even worse, jointly solving this problem and training the downstream retrieval-based systems, say RAG systems could be highly inefficient. To overcome these challenges, we propose Performance-Oriented Query Decomposer (POQD), a novel query decomposition framework for MVR. POQD leverages one LLM for query decomposition and searches the optimal prompt with an LLM-based optimizer. We further propose an end-to-end training algorithm to alternatively optimize the prompt for query decomposition and the downstream models. This algorithm can achieve superior MVR performance at a reasonable training cost as our theoretical analysis suggests. POQD can be integrated seamlessly into arbitrary retrieval-based systems such as Retrieval-Augmented Generation (RAG) systems. Extensive empirical studies on representative RAG-based QA tasks show that POQD outperforms existing query decomposition strategies in both retrieval performance and end-to-end QA accuracy. POQD is available at https://github.com/PKU-SDS-lab/POQD-ICML25.
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。