@inproceedings{nguyen-etal-2025-minielm,
title = "{M}ini{ELM}: A Lightweight and Adaptive Query Rewriting Framework for {E}-Commerce Search Optimization",
author = "Nguyen, Duy A. and
Mohan, Rishi Kesav and
Yang, Shimeng and
Akash, Pritom Saha and
Chang, Kevin Chen-Chuan",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.363/",
doi = "10.18653/v1/2025.findings-acl.363",
pages = "6952--6964",
ISBN = "979-8-89176-256-5",
abstract = "Query rewriting (QR) is a critical technique in e-commerce search, addressing the lexical gap between user queries and product descriptions to enhance search performance. Existing QR approaches typically fall into two categories: discriminative models and generative methods leveraging large language models (LLMs). Discriminative models often struggle with natural language understanding and offer limited flexibility in rewriting, while generative LLMs, despite producing high-quality rewrites, face high inference latency and cost in online settings. These limitations force offline deployment, making them vulnerable to issues like information staleness and semantic drift. To overcome these challenges, we propose a novel hybrid pipeline for QR that balances efficiency and effectiveness. Our approach combines **offline knowledge distillation** to create a lightweight but efficient student model with **online reinforcement learning (RL)** to refine query rewriting dynamically using real-time feedback. A key innovation is the use of LLMs as **simulated human feedback**, enabling scalable reward signals and cost-effective evaluation without manual annotations. Experimental results on Amazon ESCI dataset demonstrate significant improvements in query relevance, diversity, and adaptability, as well as positive feedback from the LLM simulation. This work contributes to advancing LLM capabilities for domain-specific applications, offering a robust solution for dynamic and complex e-commerce search environments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2025-minielm">
<titleInfo>
<title>MiniELM: A Lightweight and Adaptive Query Rewriting Framework for E-Commerce Search Optimization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Duy</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishi</namePart>
<namePart type="given">Kesav</namePart>
<namePart type="family">Mohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shimeng</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pritom</namePart>
<namePart type="given">Saha</namePart>
<namePart type="family">Akash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Chen-Chuan</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Query rewriting (QR) is a critical technique in e-commerce search, addressing the lexical gap between user queries and product descriptions to enhance search performance. Existing QR approaches typically fall into two categories: discriminative models and generative methods leveraging large language models (LLMs). Discriminative models often struggle with natural language understanding and offer limited flexibility in rewriting, while generative LLMs, despite producing high-quality rewrites, face high inference latency and cost in online settings. These limitations force offline deployment, making them vulnerable to issues like information staleness and semantic drift. To overcome these challenges, we propose a novel hybrid pipeline for QR that balances efficiency and effectiveness. Our approach combines **offline knowledge distillation** to create a lightweight but efficient student model with **online reinforcement learning (RL)** to refine query rewriting dynamically using real-time feedback. A key innovation is the use of LLMs as **simulated human feedback**, enabling scalable reward signals and cost-effective evaluation without manual annotations. Experimental results on Amazon ESCI dataset demonstrate significant improvements in query relevance, diversity, and adaptability, as well as positive feedback from the LLM simulation. This work contributes to advancing LLM capabilities for domain-specific applications, offering a robust solution for dynamic and complex e-commerce search environments.</abstract>
<identifier type="citekey">nguyen-etal-2025-minielm</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.363</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.363/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>6952</start>
<end>6964</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MiniELM: A Lightweight and Adaptive Query Rewriting Framework for E-Commerce Search Optimization
%A Nguyen, Duy A.
%A Mohan, Rishi Kesav
%A Yang, Shimeng
%A Akash, Pritom Saha
%A Chang, Kevin Chen-Chuan
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F nguyen-etal-2025-minielm
%X Query rewriting (QR) is a critical technique in e-commerce search, addressing the lexical gap between user queries and product descriptions to enhance search performance. Existing QR approaches typically fall into two categories: discriminative models and generative methods leveraging large language models (LLMs). Discriminative models often struggle with natural language understanding and offer limited flexibility in rewriting, while generative LLMs, despite producing high-quality rewrites, face high inference latency and cost in online settings. These limitations force offline deployment, making them vulnerable to issues like information staleness and semantic drift. To overcome these challenges, we propose a novel hybrid pipeline for QR that balances efficiency and effectiveness. Our approach combines **offline knowledge distillation** to create a lightweight but efficient student model with **online reinforcement learning (RL)** to refine query rewriting dynamically using real-time feedback. A key innovation is the use of LLMs as **simulated human feedback**, enabling scalable reward signals and cost-effective evaluation without manual annotations. Experimental results on Amazon ESCI dataset demonstrate significant improvements in query relevance, diversity, and adaptability, as well as positive feedback from the LLM simulation. This work contributes to advancing LLM capabilities for domain-specific applications, offering a robust solution for dynamic and complex e-commerce search environments.
%R 10.18653/v1/2025.findings-acl.363
%U https://aclanthology.org/2025.findings-acl.363/
%U https://doi.org/10.18653/v1/2025.findings-acl.363
%P 6952-6964
Markdown (Informal)
[MiniELM: A Lightweight and Adaptive Query Rewriting Framework for E-Commerce Search Optimization](https://aclanthology.org/2025.findings-acl.363/) (Nguyen et al., Findings 2025)
ACL