让检索系统在推理时做逻辑判断，提升复杂查询准确率
Enhancing Retrieval Systems with Inference-Time Logical Reasoning
- 将自然语言查询的逻辑结构解析后组合相似度得分
- 在多个数据集上显著提升复杂查询的检索效果
- 无需训练，兼容现有模型，适合需要精准逻辑理解的场景
传统检索方法依赖将用户查询转换为向量表示，并基于嵌入空间中的余弦相似度进行文档召回。虽然高效可扩展，但难以处理包含否定、合取、析取等逻辑结构的复杂查询。本文提出一种新的推理时逻辑推理框架，显式地将逻辑推理融入检索过程。该方法从自然语言查询中提取逻辑结构，然后组合各条目余弦相似度以生成最终文档得分。此方法在不牺牲计算效率的前提下，使检索过程能处理复杂逻辑推理。在合成与真实世界基准上的实验表明，该方法在不同模型和数据集上均持续优于传统检索方法，显著提升了复杂查询的检索性能。
原文摘要 · Abstract (English)
Traditional retrieval methods rely on transforming user queries into vector representations and retrieving documents based on cosine similarity within an embedding space. While efficient and scalable, this approach often fails to handle complex queries involving logical constructs such as negations, conjunctions, and disjunctions. In this paper, we propose a novel inference-time logical reasoning framework that explicitly incorporates logical reasoning into the retrieval process. Our method extracts logical reasoning structures from natural language queries and then composes the individual cosine similarity scores to formulate the final document scores. This approach enables the retrieval process to handle complex logical reasoning without compromising computational efficiency. Our results on both synthetic and real-world benchmarks demonstrate that the proposed method consistently outperforms traditional retrieval methods across different models and datasets, significantly improving retrieval performance for complex queries.
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。