@inproceedings{sun-etal-2026-multimodal,
title = "Multimodal Dual-Path Decoding for Medical Report Generation",
author = "Sun, Jinghan and
Wei, Dong and
Zhu, Zhihong and
Xue, Yuyang and
McDonagh, Steven and
Wu, Xian",
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.1997/",
doi = "10.18653/v1/2026.findings-acl.1997",
pages = "40193--40204",
ISBN = "979-8-89176-395-1",
abstract = "Radiology report generation requires precise alignment between medical imaging findings and clinically coherent textual descriptions. While current methods predominantly rely on either large vision-language models (LVLMs) for visual grounding or large language models (LLMs) for medical narrative generation, they often fail to effectively integrate multimodal clinical evidence with domain-specific knowledge. This paper proposes a novel multimodal dual-path framework that synergistically combines LVLMs and LLMs to address these limitations. Our approach establishes a dynamic fusion between LVLMs' visual-semantic grounding capabilities and LLMs' clinical knowledge reasoning. Specifically, we employ a structured prompting strategy that models the report generation task into three clinically meaningful sections and introduces fine-grained multi-label classification prompts to guide the models, enabling more accurate and comprehensive clinical report generation. Experiments on the public MIMIC-CXR benchmark demonstrate our framework{'}s superiority over state-of-the-art methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2026-multimodal">
<titleInfo>
<title>Multimodal Dual-Path Decoding for Medical Report Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinghan</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhihong</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuyang</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">McDonagh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Wu</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>Radiology report generation requires precise alignment between medical imaging findings and clinically coherent textual descriptions. While current methods predominantly rely on either large vision-language models (LVLMs) for visual grounding or large language models (LLMs) for medical narrative generation, they often fail to effectively integrate multimodal clinical evidence with domain-specific knowledge. This paper proposes a novel multimodal dual-path framework that synergistically combines LVLMs and LLMs to address these limitations. Our approach establishes a dynamic fusion between LVLMs’ visual-semantic grounding capabilities and LLMs’ clinical knowledge reasoning. Specifically, we employ a structured prompting strategy that models the report generation task into three clinically meaningful sections and introduces fine-grained multi-label classification prompts to guide the models, enabling more accurate and comprehensive clinical report generation. Experiments on the public MIMIC-CXR benchmark demonstrate our framework’s superiority over state-of-the-art methods.</abstract>
<identifier type="citekey">sun-etal-2026-multimodal</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1997</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1997/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>40193</start>
<end>40204</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Dual-Path Decoding for Medical Report Generation
%A Sun, Jinghan
%A Wei, Dong
%A Zhu, Zhihong
%A Xue, Yuyang
%A McDonagh, Steven
%A Wu, Xian
%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-multimodal
%X Radiology report generation requires precise alignment between medical imaging findings and clinically coherent textual descriptions. While current methods predominantly rely on either large vision-language models (LVLMs) for visual grounding or large language models (LLMs) for medical narrative generation, they often fail to effectively integrate multimodal clinical evidence with domain-specific knowledge. This paper proposes a novel multimodal dual-path framework that synergistically combines LVLMs and LLMs to address these limitations. Our approach establishes a dynamic fusion between LVLMs’ visual-semantic grounding capabilities and LLMs’ clinical knowledge reasoning. Specifically, we employ a structured prompting strategy that models the report generation task into three clinically meaningful sections and introduces fine-grained multi-label classification prompts to guide the models, enabling more accurate and comprehensive clinical report generation. Experiments on the public MIMIC-CXR benchmark demonstrate our framework’s superiority over state-of-the-art methods.
%R 10.18653/v1/2026.findings-acl.1997
%U https://aclanthology.org/2026.findings-acl.1997/
%U https://doi.org/10.18653/v1/2026.findings-acl.1997
%P 40193-40204
Markdown (Informal)
[Multimodal Dual-Path Decoding for Medical Report Generation](https://aclanthology.org/2026.findings-acl.1997/) (Sun et al., Findings 2026)
ACL
- Jinghan Sun, Dong Wei, Zhihong Zhu, Yuyang Xue, Steven McDonagh, and Xian Wu. 2026. Multimodal Dual-Path Decoding for Medical Report Generation. In Findings of the Association for Computational Linguistics: ACL 2026, pages 40193–40204, San Diego, California, United States. Association for Computational Linguistics.