@inproceedings{sun-etal-2026-q2ei,
title = "{Q}2{EI}: Query-to-Entity Inference for Semantic Condensation in Domain-Specific Retrieval",
author = "Sun, Yixuan and
Xu, Zhenqin and
Zhai, HanFeng and
Yu, Zishu and
Peng, Xiaohui",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1791/",
doi = "10.18653/v1/2026.findings-acl.1791",
pages = "35943--35958",
ISBN = "979-8-89176-395-1",
abstract = "Retrieval-Augmented Generation (RAG) remains unreliable in specialized domains due to semantic and lexical mismatch between lay queries and professional terminology, and existing generative expansion often introduces redundancy or hallucinations that cause semantic drift. We propose Generative Query Condensation (GQC), a query rewriting strategy that reframes rewriting as semantic condensation rather than expansion. To operationalize GQC, we introduce Query-to-Entity Inference (Q2EI), an entity-centric rewriting method that realizes semantic condensation through explicit inference of the underlying target entity. By moving semantic alignment from retrieval-time vector matching to the rewriting stage, Q2EI produces information-dense query representations. Experimental results on medical and legal benchmarks show that Q2EI consistently outperforms strong baselines across retrievers, improving retrieval effectiveness while substantially reducing rewriting token consumption compared to generative expansion methods. Further analysis confirms that these gains primarily arise from accurate entity inference, and that Q2EI{'}s semantic condensation design limits error amplification when inference is imperfect, leading to more stable and interpretable retrieval behavior."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2026-q2ei">
<titleInfo>
<title>Q2EI: Query-to-Entity Inference for Semantic Condensation in Domain-Specific Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yixuan</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenqin</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">HanFeng</namePart>
<namePart type="family">Zhai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zishu</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaohui</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Retrieval-Augmented Generation (RAG) remains unreliable in specialized domains due to semantic and lexical mismatch between lay queries and professional terminology, and existing generative expansion often introduces redundancy or hallucinations that cause semantic drift. We propose Generative Query Condensation (GQC), a query rewriting strategy that reframes rewriting as semantic condensation rather than expansion. To operationalize GQC, we introduce Query-to-Entity Inference (Q2EI), an entity-centric rewriting method that realizes semantic condensation through explicit inference of the underlying target entity. By moving semantic alignment from retrieval-time vector matching to the rewriting stage, Q2EI produces information-dense query representations. Experimental results on medical and legal benchmarks show that Q2EI consistently outperforms strong baselines across retrievers, improving retrieval effectiveness while substantially reducing rewriting token consumption compared to generative expansion methods. Further analysis confirms that these gains primarily arise from accurate entity inference, and that Q2EI’s semantic condensation design limits error amplification when inference is imperfect, leading to more stable and interpretable retrieval behavior.</abstract>
<identifier type="citekey">sun-etal-2026-q2ei</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1791</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1791/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>35943</start>
<end>35958</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Q2EI: Query-to-Entity Inference for Semantic Condensation in Domain-Specific Retrieval
%A Sun, Yixuan
%A Xu, Zhenqin
%A Zhai, HanFeng
%A Yu, Zishu
%A Peng, Xiaohui
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F sun-etal-2026-q2ei
%X Retrieval-Augmented Generation (RAG) remains unreliable in specialized domains due to semantic and lexical mismatch between lay queries and professional terminology, and existing generative expansion often introduces redundancy or hallucinations that cause semantic drift. We propose Generative Query Condensation (GQC), a query rewriting strategy that reframes rewriting as semantic condensation rather than expansion. To operationalize GQC, we introduce Query-to-Entity Inference (Q2EI), an entity-centric rewriting method that realizes semantic condensation through explicit inference of the underlying target entity. By moving semantic alignment from retrieval-time vector matching to the rewriting stage, Q2EI produces information-dense query representations. Experimental results on medical and legal benchmarks show that Q2EI consistently outperforms strong baselines across retrievers, improving retrieval effectiveness while substantially reducing rewriting token consumption compared to generative expansion methods. Further analysis confirms that these gains primarily arise from accurate entity inference, and that Q2EI’s semantic condensation design limits error amplification when inference is imperfect, leading to more stable and interpretable retrieval behavior.
%R 10.18653/v1/2026.findings-acl.1791
%U https://aclanthology.org/2026.findings-acl.1791/
%U https://doi.org/10.18653/v1/2026.findings-acl.1791
%P 35943-35958
Markdown (Informal)
[Q2EI: Query-to-Entity Inference for Semantic Condensation in Domain-Specific Retrieval](https://aclanthology.org/2026.findings-acl.1791/) (Sun et al., Findings 2026)
ACL