@inproceedings{li-etal-2025-unirag,
title = "{U}ni{RAG}: Unified Query Understanding Method for Retrieval Augmented Generation",
author = "Li, Rui and
He, Liyang and
Liu, Qi and
Zhang, Zheng and
Yu, Heng and
Ye, Yuyang and
Zhu, Linbo and
Su, Yu",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.693/",
doi = "10.18653/v1/2025.acl-long.693",
pages = "14163--14178",
ISBN = "979-8-89176-251-0",
abstract = "Retrieval-Augmented Generation (RAG) technology effectively addresses the issues of knowledge update lag and hallucinations in large language models (LLMs) by integrating internal and external knowledge. Existing query augmentation methods improve RAG{'}s performance in handling complex queries but face two key challenges: (1) the separation of query augmentation and encoding tasks, which hinders information sharing and introduces cumulative errors, and (2) the difficulty of selecting the optimal augmentation strategy for different scenarios. In this work, we propose UniRAG, a unified framework for query understanding in RAG. UniRAG employs a decoder-only LLM to jointly perform query augmentation and encoding, eliminating task separation. To facilitate adaptive query augmentation, we categorize existing techniques into query paraphrasing, query expansion, and query abstraction. Our model learns to select the optimal augmentation strategy based on user queries, leveraging retrieval and generation outputs as feedback. Experimental results show that UniRAG significantly outperforms traditional query augmentation methods in five knowledge-intensive benchmark tasks in both closed and open domain question answering."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-unirag">
<titleInfo>
<title>UniRAG: Unified Query Understanding Method for Retrieval Augmented Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liyang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuyang</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linbo</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Su</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>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Retrieval-Augmented Generation (RAG) technology effectively addresses the issues of knowledge update lag and hallucinations in large language models (LLMs) by integrating internal and external knowledge. Existing query augmentation methods improve RAG’s performance in handling complex queries but face two key challenges: (1) the separation of query augmentation and encoding tasks, which hinders information sharing and introduces cumulative errors, and (2) the difficulty of selecting the optimal augmentation strategy for different scenarios. In this work, we propose UniRAG, a unified framework for query understanding in RAG. UniRAG employs a decoder-only LLM to jointly perform query augmentation and encoding, eliminating task separation. To facilitate adaptive query augmentation, we categorize existing techniques into query paraphrasing, query expansion, and query abstraction. Our model learns to select the optimal augmentation strategy based on user queries, leveraging retrieval and generation outputs as feedback. Experimental results show that UniRAG significantly outperforms traditional query augmentation methods in five knowledge-intensive benchmark tasks in both closed and open domain question answering.</abstract>
<identifier type="citekey">li-etal-2025-unirag</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.693</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.693/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>14163</start>
<end>14178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UniRAG: Unified Query Understanding Method for Retrieval Augmented Generation
%A Li, Rui
%A He, Liyang
%A Liu, Qi
%A Zhang, Zheng
%A Yu, Heng
%A Ye, Yuyang
%A Zhu, Linbo
%A Su, Yu
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F li-etal-2025-unirag
%X Retrieval-Augmented Generation (RAG) technology effectively addresses the issues of knowledge update lag and hallucinations in large language models (LLMs) by integrating internal and external knowledge. Existing query augmentation methods improve RAG’s performance in handling complex queries but face two key challenges: (1) the separation of query augmentation and encoding tasks, which hinders information sharing and introduces cumulative errors, and (2) the difficulty of selecting the optimal augmentation strategy for different scenarios. In this work, we propose UniRAG, a unified framework for query understanding in RAG. UniRAG employs a decoder-only LLM to jointly perform query augmentation and encoding, eliminating task separation. To facilitate adaptive query augmentation, we categorize existing techniques into query paraphrasing, query expansion, and query abstraction. Our model learns to select the optimal augmentation strategy based on user queries, leveraging retrieval and generation outputs as feedback. Experimental results show that UniRAG significantly outperforms traditional query augmentation methods in five knowledge-intensive benchmark tasks in both closed and open domain question answering.
%R 10.18653/v1/2025.acl-long.693
%U https://aclanthology.org/2025.acl-long.693/
%U https://doi.org/10.18653/v1/2025.acl-long.693
%P 14163-14178
Markdown (Informal)
[UniRAG: Unified Query Understanding Method for Retrieval Augmented Generation](https://aclanthology.org/2025.acl-long.693/) (Li et al., ACL 2025)
ACL
- Rui Li, Liyang He, Qi Liu, Zheng Zhang, Heng Yu, Yuyang Ye, Linbo Zhu, and Yu Su. 2025. UniRAG: Unified Query Understanding Method for Retrieval Augmented Generation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14163–14178, Vienna, Austria. Association for Computational Linguistics.