让检索模型自动选择快慢推理模式，又快又好。
Your Dense Retriever is Secretly an Expeditious Reasoner
- 根据查询复杂度自动选快速嵌入推理或深度LLM推理
- 在BRIGHT数据集上降低28%计算成本，效果提升7%
- 适合需要高效且精准检索的场景，如问答系统
密集检索器通过将查询和文档编码为连续向量来提升检索效果，但在处理需要推理的查询时表现不佳。尽管大型语言模型（LLMs）可重写查询以捕捉复杂推理，但普遍应用会带来高昂计算开销。本文提出自适应查询推理（AdaQR），一种混合查询重写框架。其中，推理路由器动态决定每个查询应采用快速密集推理或深层LLM推理。密集推理由密集推理器实现，直接在嵌入空间中进行类LLM推理，可在效率与准确率间可控权衡。在大规模检索基准BRIGHT上的实验表明，AdaQR将推理成本降低28%，同时保留甚至提升了7%的检索性能。
原文摘要 · Abstract (English)
Dense retrievers enhance retrieval by encoding queries and documents into continuous vectors, but they often struggle with reasoning-intensive queries. Although Large Language Models (LLMs) can reformulate queries to capture complex reasoning, applying them universally incurs significant computational cost. In this work, we propose Adaptive Query Reasoning (AdaQR), a hybrid query rewriting framework. Within this framework, a Reasoner Router dynamically directs each query to either fast dense reasoning or deep LLM reasoning. The dense reasoning is achieved by the Dense Reasoner, which performs LLM-style reasoning directly in the embedding space, enabling a controllable trade-off between efficiency and accuracy. Experiments on large-scale retrieval benchmarks BRIGHT show that AdaQR reduces reasoning cost by 28% while preserving-or even improving-retrieval performance by 7%.
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。