@inproceedings{min-etal-2026-progressive,
title = "Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning",
author = "Min, Zhu and
Hao, Yanchao and
Liu, Jian and
He, Shizhu and
Chen, Xi",
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.2045/",
pages = "41135--41147",
ISBN = "979-8-89176-395-1",
abstract = "Retrieval-augmented generation (RAG) can enhance large language models (LLMs) by providing external knowledge and helping reduce hallucinations. In multimodal RAG, however, retrieval remains challenging because a single retriever may fail to capture fine-grained multimodal semantics, and visually or semantically similar entities may still contain misleading information for answer generation. We propose a progressive multimodal re-ranking framework with curriculum learning to improve CLIP-based visual coarse-grained retrieval. Our framework progressively refines retrieval results through two stages: fine-grained section-level re-ranking and multimodal section reassessment. To better align re-ranking with multimodal queries, we introduce a curriculum-learning strategy that trains the model with hard negatives that are visually or semantically similar but contain misleading information. Experiments on InfoSeek and Enc-VQA show that our method achieves state-of-the-art answer accuracy and competitive retrieval performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="min-etal-2026-progressive">
<titleInfo>
<title>Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhu</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanchao</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Chen</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) can enhance large language models (LLMs) by providing external knowledge and helping reduce hallucinations. In multimodal RAG, however, retrieval remains challenging because a single retriever may fail to capture fine-grained multimodal semantics, and visually or semantically similar entities may still contain misleading information for answer generation. We propose a progressive multimodal re-ranking framework with curriculum learning to improve CLIP-based visual coarse-grained retrieval. Our framework progressively refines retrieval results through two stages: fine-grained section-level re-ranking and multimodal section reassessment. To better align re-ranking with multimodal queries, we introduce a curriculum-learning strategy that trains the model with hard negatives that are visually or semantically similar but contain misleading information. Experiments on InfoSeek and Enc-VQA show that our method achieves state-of-the-art answer accuracy and competitive retrieval performance.</abstract>
<identifier type="citekey">min-etal-2026-progressive</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.2045/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>41135</start>
<end>41147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning
%A Min, Zhu
%A Hao, Yanchao
%A Liu, Jian
%A He, Shizhu
%A Chen, Xi
%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 min-etal-2026-progressive
%X Retrieval-augmented generation (RAG) can enhance large language models (LLMs) by providing external knowledge and helping reduce hallucinations. In multimodal RAG, however, retrieval remains challenging because a single retriever may fail to capture fine-grained multimodal semantics, and visually or semantically similar entities may still contain misleading information for answer generation. We propose a progressive multimodal re-ranking framework with curriculum learning to improve CLIP-based visual coarse-grained retrieval. Our framework progressively refines retrieval results through two stages: fine-grained section-level re-ranking and multimodal section reassessment. To better align re-ranking with multimodal queries, we introduce a curriculum-learning strategy that trains the model with hard negatives that are visually or semantically similar but contain misleading information. Experiments on InfoSeek and Enc-VQA show that our method achieves state-of-the-art answer accuracy and competitive retrieval performance.
%U https://aclanthology.org/2026.findings-acl.2045/
%P 41135-41147
Markdown (Informal)
[Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning](https://aclanthology.org/2026.findings-acl.2045/) (Min et al., Findings 2026)
ACL