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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Siddiqui, Emad, Terikuti, Venkatesh, Lu, Xuan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917219408019456
author Siddiqui, Emad
Terikuti, Venkatesh
Lu, Xuan
author_facet Siddiqui, Emad
Terikuti, Venkatesh
Lu, Xuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16492
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LLM-based Semantic Search for Conversational Queries in E-commerce
Siddiqui, Emad
Terikuti, Venkatesh
Lu, Xuan
Information Retrieval
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.
title LLM-based Semantic Search for Conversational Queries in E-commerce
topic Information Retrieval
url https://arxiv.org/abs/2601.16492