@inproceedings{sun-etal-2026-beyond-query,
title = "Beyond Query Bias: Candidate-Aware Iterative Refinement for Zero-Shot Composed Image Retrieval",
author = "Sun, Nan and
Tang, Jing and
Sun, Lei and
Chen, Rui and
Lu, Yuxing and
Chu, Xiangxiang and
Ling, Hefei and
Cai, Yujun",
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.1120/",
pages = "22318--22329",
ISBN = "979-8-89176-395-1",
abstract = "Zero-Shot Composed Image Retrieval (ZS-CIR) retrieves target images using a reference image and modification text without task-specific training. Existing methods typically rely on MLLMs to generate query vectors with pre-trained models like CLIP. However, those constructed queries suffer from inherent cognitive bias due to unknown candidate distribution. We propose CoRR, a training-free framework that reframes ZS-CIR as a self-correcting process through bias-aware query refinement. CoRR uses retrieved results as feedback to perceive the candidate distribution. With carefully designed CoT prompting, the MLLM inspects the retrieved candidates to identify intent misalignments in the query and then corrects them via Historical Query Fusion. We also introduce Retrieval-Driven Caption Optimization to provide context-aligned examples, reducing phrasing and style mismatches. Experiments on public benchmarks show that CoRR significantly outperforms other SOTA methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2026-beyond-query">
<titleInfo>
<title>Beyond Query Bias: Candidate-Aware Iterative Refinement for Zero-Shot Composed Image Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxing</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangxiang</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hefei</namePart>
<namePart type="family">Ling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yujun</namePart>
<namePart type="family">Cai</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>Zero-Shot Composed Image Retrieval (ZS-CIR) retrieves target images using a reference image and modification text without task-specific training. Existing methods typically rely on MLLMs to generate query vectors with pre-trained models like CLIP. However, those constructed queries suffer from inherent cognitive bias due to unknown candidate distribution. We propose CoRR, a training-free framework that reframes ZS-CIR as a self-correcting process through bias-aware query refinement. CoRR uses retrieved results as feedback to perceive the candidate distribution. With carefully designed CoT prompting, the MLLM inspects the retrieved candidates to identify intent misalignments in the query and then corrects them via Historical Query Fusion. We also introduce Retrieval-Driven Caption Optimization to provide context-aligned examples, reducing phrasing and style mismatches. Experiments on public benchmarks show that CoRR significantly outperforms other SOTA methods.</abstract>
<identifier type="citekey">sun-etal-2026-beyond-query</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1120/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>22318</start>
<end>22329</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Query Bias: Candidate-Aware Iterative Refinement for Zero-Shot Composed Image Retrieval
%A Sun, Nan
%A Tang, Jing
%A Sun, Lei
%A Chen, Rui
%A Lu, Yuxing
%A Chu, Xiangxiang
%A Ling, Hefei
%A Cai, Yujun
%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-beyond-query
%X Zero-Shot Composed Image Retrieval (ZS-CIR) retrieves target images using a reference image and modification text without task-specific training. Existing methods typically rely on MLLMs to generate query vectors with pre-trained models like CLIP. However, those constructed queries suffer from inherent cognitive bias due to unknown candidate distribution. We propose CoRR, a training-free framework that reframes ZS-CIR as a self-correcting process through bias-aware query refinement. CoRR uses retrieved results as feedback to perceive the candidate distribution. With carefully designed CoT prompting, the MLLM inspects the retrieved candidates to identify intent misalignments in the query and then corrects them via Historical Query Fusion. We also introduce Retrieval-Driven Caption Optimization to provide context-aligned examples, reducing phrasing and style mismatches. Experiments on public benchmarks show that CoRR significantly outperforms other SOTA methods.
%U https://aclanthology.org/2026.findings-acl.1120/
%P 22318-22329
Markdown (Informal)
[Beyond Query Bias: Candidate-Aware Iterative Refinement for Zero-Shot Composed Image Retrieval](https://aclanthology.org/2026.findings-acl.1120/) (Sun et al., Findings 2026)
ACL
- Nan Sun, Jing Tang, Lei Sun, Rui Chen, Yuxing Lu, Xiangxiang Chu, Hefei Ling, and Yujun Cai. 2026. Beyond Query Bias: Candidate-Aware Iterative Refinement for Zero-Shot Composed Image Retrieval. In Findings of the Association for Computational Linguistics: ACL 2026, pages 22318–22329, San Diego, California, United States. Association for Computational Linguistics.