用大模型解析电商查询中的隐含需求，提升搜索精准度。
Hint-Augmented Re-ranking: Efficient Product Search using LLM-Based Query Decomposition
- 通过大模型提取查询中的属性-值提示，实现高效检索
- 相比基线，MAP提升10.9点，MRR提升5.9点
- 将大模型理解能力迁移至轻量模型，兼顾效果与速度
带有最高级词（如‘最好’、‘最热门’）的搜索查询需在多个维度上比较候选结果，要求语言理解与领域知识。我们展示大模型可通过框架提取此类表达背后的结构化语义提示，即‘隐含意图’。该方法在召回同时生成属性-值提示，可高效集成到排序流程中。实验表明，该方法在MAP上比基线提升10.9点，在MRR上提升5.9点。针对直接使用大模型重排序带来的高延迟问题，我们提出一种将最高级语义迁移到轻量模型的高效方法。研究揭示了如何表示与迁移最高级语义，推动检索系统中的语言理解，同时满足实际部署约束。
原文摘要 · Abstract (English)
Search queries with superlatives (e.g., best, most popular) require comparing candidates across multiple dimensions, demanding linguistic understanding and domain knowledge. We show that LLMs can uncover latent intent behind these expressions in e-commerce queries through a framework that extracts structured interpretations or hints. Our approach decomposes queries into attribute-value hints generated concurrently with retrieval, enabling efficient integration into the ranking pipeline. Our method improves search performanc eby 10.9 points in MAP and ranking by 5.9 points in MRR over baselines. Since direct LLM-based reranking faces prohibitive latency, we develop an efficient approach transferring superlative interpretations to lightweight models. Our findings provide insights into how superlative semantics can be represented and transferred between models, advancing linguistic interpretation in retrieval systems while addressing practical deployment constraints.
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。