@inproceedings{park-etal-2026-ra,
title = "{RA}-{RRG}: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction",
author = "Park, Jonggwon and
Yoon, Byungmu and
Kim, Soobum and
Choi, Kyoyun",
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.247/",
pages = "5029--5048",
ISBN = "979-8-89176-395-1",
abstract = "Automated radiology report generation (RRG) holds potential to reduce the workload of radiologists, and recent advances in multimodal large language models (MLLMs) have enabled multimodal chest X-ray (CXR) report generation. However, existing MLLMs are computationally expensive, require large-scale training data, and may produce hallucinated content, limiting their practical deployment. To address these limitations, we propose RA-RRG, a retrieval-augmented RRG framework that combines multimodal retrieval with large language models (LLMs) to generate radiology reports while reducing hallucinations and computational demands. RA-RRG uses LLMs to extract clinically essential key phrases from radiology reports and retrieves relevant phrases given an input image. By conditioning LLMs on the retrieved phrases, RA-RRG effectively suppresses hallucinations while maintaining strong report generation performance. Experiments on the MIMIC-CXR and IU X-ray datasets show state-of-the-art results on CheXbert metrics and competitive RadGraph F1 scores compared to MLLMs. Furthermore, RA-RRG naturally generalizes to multi-view RRG by aggregating phrases retrieved from multiple images, highlighting its broad applicability to real-world clinical scenarios. Code is available at https://github.com/deepnoid-ai/RA-RRG."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2026-ra">
<titleInfo>
<title>RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonggwon</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byungmu</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soobum</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyoyun</namePart>
<namePart type="family">Choi</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>Automated radiology report generation (RRG) holds potential to reduce the workload of radiologists, and recent advances in multimodal large language models (MLLMs) have enabled multimodal chest X-ray (CXR) report generation. However, existing MLLMs are computationally expensive, require large-scale training data, and may produce hallucinated content, limiting their practical deployment. To address these limitations, we propose RA-RRG, a retrieval-augmented RRG framework that combines multimodal retrieval with large language models (LLMs) to generate radiology reports while reducing hallucinations and computational demands. RA-RRG uses LLMs to extract clinically essential key phrases from radiology reports and retrieves relevant phrases given an input image. By conditioning LLMs on the retrieved phrases, RA-RRG effectively suppresses hallucinations while maintaining strong report generation performance. Experiments on the MIMIC-CXR and IU X-ray datasets show state-of-the-art results on CheXbert metrics and competitive RadGraph F1 scores compared to MLLMs. Furthermore, RA-RRG naturally generalizes to multi-view RRG by aggregating phrases retrieved from multiple images, highlighting its broad applicability to real-world clinical scenarios. Code is available at https://github.com/deepnoid-ai/RA-RRG.</abstract>
<identifier type="citekey">park-etal-2026-ra</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.247/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>5029</start>
<end>5048</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction
%A Park, Jonggwon
%A Yoon, Byungmu
%A Kim, Soobum
%A Choi, Kyoyun
%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 park-etal-2026-ra
%X Automated radiology report generation (RRG) holds potential to reduce the workload of radiologists, and recent advances in multimodal large language models (MLLMs) have enabled multimodal chest X-ray (CXR) report generation. However, existing MLLMs are computationally expensive, require large-scale training data, and may produce hallucinated content, limiting their practical deployment. To address these limitations, we propose RA-RRG, a retrieval-augmented RRG framework that combines multimodal retrieval with large language models (LLMs) to generate radiology reports while reducing hallucinations and computational demands. RA-RRG uses LLMs to extract clinically essential key phrases from radiology reports and retrieves relevant phrases given an input image. By conditioning LLMs on the retrieved phrases, RA-RRG effectively suppresses hallucinations while maintaining strong report generation performance. Experiments on the MIMIC-CXR and IU X-ray datasets show state-of-the-art results on CheXbert metrics and competitive RadGraph F1 scores compared to MLLMs. Furthermore, RA-RRG naturally generalizes to multi-view RRG by aggregating phrases retrieved from multiple images, highlighting its broad applicability to real-world clinical scenarios. Code is available at https://github.com/deepnoid-ai/RA-RRG.
%U https://aclanthology.org/2026.findings-acl.247/
%P 5029-5048
Markdown (Informal)
[RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction](https://aclanthology.org/2026.findings-acl.247/) (Park et al., Findings 2026)
ACL