LLM-based Semantic Search for Conversational Queries in E-commerce

TL;DR

This paper introduces an LLM-based semantic search system for e-commerce that improves understanding of conversational queries by combining domain-specific embeddings and structured filters, trained with synthetic data.

Contribution

It presents a novel framework integrating semantic embeddings and structured filtering for conversational search, using synthetic data for effective model fine-tuning.

Findings

Achieves higher precision and recall than baseline methods.

Effectively captures user intent from conversational queries.

Demonstrates robustness across different e-commerce datasets.

Abstract

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.