IterQR: An Iterative Framework for LLM-based Query Rewrite in e-Commercial Search System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Shangyu, Jia, Xinyu, Zhang, Yingfei, Zhang, Shuai, Li, Xiang, Lin, Wei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915232337625088
author Chen, Shangyu
Jia, Xinyu
Zhang, Yingfei
Zhang, Shuai
Li, Xiang
Lin, Wei
author_facet Chen, Shangyu
Jia, Xinyu
Zhang, Yingfei
Zhang, Shuai
Li, Xiang
Lin, Wei
contents The essence of modern e-Commercial search system lies in matching user's intent and available candidates depending on user's query, providing personalized and precise service. However, user's query may be incorrect due to ambiguous input and typo, leading to inaccurate search. These cases may be released by query rewrite: modify query to other representation or expansion. However, traditional query rewrite replies on static rewrite vocabulary, which is manually established meanwhile lacks interaction with both domain knowledge in e-Commercial system and common knowledge in the real world. In this paper, with the ability to generate text content of Large Language Models (LLMs), we provide an iterative framework to generate query rewrite. The framework incorporates a 3-stage procedure in each iteration: Rewrite Generation with domain knowledge by Retrieval-Augmented Generation (RAG) and query understanding by Chain-of-Thoughts (CoT); Online Signal Collection with automatic positive rewrite update; Post-training of LLM with multi task objective to generate new rewrites. Our work (named as IterQR) provides a comprehensive framework to generate \textbf{Q}uery \textbf{R}ewrite with both domain / real-world knowledge. It automatically update and self-correct the rewrites during \textbf{iter}ations. \method{} has been deployed in Meituan Delivery's search system (China's leading food delivery platform), providing service for users with significant improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05309
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle IterQR: An Iterative Framework for LLM-based Query Rewrite in e-Commercial Search System
Chen, Shangyu
Jia, Xinyu
Zhang, Yingfei
Zhang, Shuai
Li, Xiang
Lin, Wei
Information Retrieval
Artificial Intelligence
The essence of modern e-Commercial search system lies in matching user's intent and available candidates depending on user's query, providing personalized and precise service. However, user's query may be incorrect due to ambiguous input and typo, leading to inaccurate search. These cases may be released by query rewrite: modify query to other representation or expansion. However, traditional query rewrite replies on static rewrite vocabulary, which is manually established meanwhile lacks interaction with both domain knowledge in e-Commercial system and common knowledge in the real world. In this paper, with the ability to generate text content of Large Language Models (LLMs), we provide an iterative framework to generate query rewrite. The framework incorporates a 3-stage procedure in each iteration: Rewrite Generation with domain knowledge by Retrieval-Augmented Generation (RAG) and query understanding by Chain-of-Thoughts (CoT); Online Signal Collection with automatic positive rewrite update; Post-training of LLM with multi task objective to generate new rewrites. Our work (named as IterQR) provides a comprehensive framework to generate \textbf{Q}uery \textbf{R}ewrite with both domain / real-world knowledge. It automatically update and self-correct the rewrites during \textbf{iter}ations. \method{} has been deployed in Meituan Delivery's search system (China's leading food delivery platform), providing service for users with significant improvement.
title IterQR: An Iterative Framework for LLM-based Query Rewrite in e-Commercial Search System
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2504.05309