LLM-based Semantic Search for Conversational Queries in E-commerce
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| 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 |