用大模型理解电商对话式搜索，提升精准度
LLM-based Semantic Search for Conversational Queries in E-commerce
- 结合领域嵌入与结构化过滤，理解对话查询意图
- 合成数据训练双模型，召回率与准确率显著提升
- 适合需要理解复杂用户表达的电商搜索场景
对话式用户查询正日益挑战传统电商搜索系统，这些系统通常针对关键词查询优化。本文提出一种基于大语言模型的语义搜索框架，通过结合领域特定嵌入与结构化过滤，有效捕捉对话查询中的用户意图。为应对标注数据有限的问题，我们利用大模型生成合成数据，用于微调两个模型：一个嵌入模型，使语义相似商品在表示空间中靠近；一个生成模型，将自然语言查询转化为结构化约束。通过融合基于相似性的检索与基于约束的过滤，该框架在真实世界数据集上相较于基线方法，在多种设置下均实现了更强的精确率与召回率。
原文摘要 · Abstract (English)
Conversational user queries are increasingly challenging traditional e-commerce platforms, whose search systems are typically optimized for keyword-based queries. We present an LLM-based semantic search framework that effectively captures user intent from conversational queries by combining domain-specific embeddings with structured filters. To address the challenge of limited labeled data, we generate synthetic data using LLMs to guide the fine-tuning of two models: an embedding model that positions semantically similar products close together in the representation space, and a generative model for converting natural language queries into structured constraints. By combining similarity-based retrieval with constraint-based filtering, our framework achieves strong precision and recall across various settings compared to baseline approaches on a real-world dataset.
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。