@inproceedings{nagar-etal-2025-umedsum,
title = "u{M}ed{S}um: A Unified Framework for Clinical Abstractive Summarization",
author = "Nagar, Aishik and
Liu, Yutong and
Liu, Andy T. and
Schlegel, Viktor and
Dwivedi, Vijay Prakash and
Kaliya-Perumal, Arun-Kumar and
Kalanchiam, Guna Pratheep and
Tang, Yili and
Tan, Robby T.",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.134/",
doi = "10.18653/v1/2025.acl-long.134",
pages = "2653--2672",
ISBN = "979-8-89176-251-0",
abstract = "Clinical abstractive summarization struggles to balance faithfulness and informativeness, sacrificing key information or introducing confabulations. Techniques like in-context learning and fine-tuning have improved overall summary quality orthogonally, without considering the above issue. Conversely, methods aimed at improving faithfulness and informativeness, such as model reasoning and self improvement, have not been systematically evaluated in the clinical domain. We address this gap by first performing a comprehensive benchmark and study of six advanced abstractive summarization methods across three datasets using five reference-based and reference-free metrics, with the latter specifically assessing faithfulness and informativeness. Based on its findings we then develop uMedSum, a modular hybrid framework introducing novel approaches for sequential confabulation removal and key information addition. Our work outperforms previous GPT-4-based state-of-the-art (SOTA) methods in both quantitative metrics and expert evaluations, achieving an 11.8{\%} average improvement in dedicated faithfulness metrics over the previous SOTA. Doctors prefer uMedSum{'}s summaries 6 times more than previous SOTA in difficult cases containing confabulations or missing information. These results highlight uMedSum{'}s effectiveness and generalizability across various datasets and metrics, marking a significant advancement in clinical summarization. uMedSum toolkit is made available on GitHub."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nagar-etal-2025-umedsum">
<titleInfo>
<title>uMedSum: A Unified Framework for Clinical Abstractive Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aishik</namePart>
<namePart type="family">Nagar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viktor</namePart>
<namePart type="family">Schlegel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vijay</namePart>
<namePart type="given">Prakash</namePart>
<namePart type="family">Dwivedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arun-Kumar</namePart>
<namePart type="family">Kaliya-Perumal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guna</namePart>
<namePart type="given">Pratheep</namePart>
<namePart type="family">Kalanchiam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yili</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robby</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Clinical abstractive summarization struggles to balance faithfulness and informativeness, sacrificing key information or introducing confabulations. Techniques like in-context learning and fine-tuning have improved overall summary quality orthogonally, without considering the above issue. Conversely, methods aimed at improving faithfulness and informativeness, such as model reasoning and self improvement, have not been systematically evaluated in the clinical domain. We address this gap by first performing a comprehensive benchmark and study of six advanced abstractive summarization methods across three datasets using five reference-based and reference-free metrics, with the latter specifically assessing faithfulness and informativeness. Based on its findings we then develop uMedSum, a modular hybrid framework introducing novel approaches for sequential confabulation removal and key information addition. Our work outperforms previous GPT-4-based state-of-the-art (SOTA) methods in both quantitative metrics and expert evaluations, achieving an 11.8% average improvement in dedicated faithfulness metrics over the previous SOTA. Doctors prefer uMedSum’s summaries 6 times more than previous SOTA in difficult cases containing confabulations or missing information. These results highlight uMedSum’s effectiveness and generalizability across various datasets and metrics, marking a significant advancement in clinical summarization. uMedSum toolkit is made available on GitHub.</abstract>
<identifier type="citekey">nagar-etal-2025-umedsum</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.134</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.134/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>2653</start>
<end>2672</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T uMedSum: A Unified Framework for Clinical Abstractive Summarization
%A Nagar, Aishik
%A Liu, Yutong
%A Liu, Andy T.
%A Schlegel, Viktor
%A Dwivedi, Vijay Prakash
%A Kaliya-Perumal, Arun-Kumar
%A Kalanchiam, Guna Pratheep
%A Tang, Yili
%A Tan, Robby T.
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F nagar-etal-2025-umedsum
%X Clinical abstractive summarization struggles to balance faithfulness and informativeness, sacrificing key information or introducing confabulations. Techniques like in-context learning and fine-tuning have improved overall summary quality orthogonally, without considering the above issue. Conversely, methods aimed at improving faithfulness and informativeness, such as model reasoning and self improvement, have not been systematically evaluated in the clinical domain. We address this gap by first performing a comprehensive benchmark and study of six advanced abstractive summarization methods across three datasets using five reference-based and reference-free metrics, with the latter specifically assessing faithfulness and informativeness. Based on its findings we then develop uMedSum, a modular hybrid framework introducing novel approaches for sequential confabulation removal and key information addition. Our work outperforms previous GPT-4-based state-of-the-art (SOTA) methods in both quantitative metrics and expert evaluations, achieving an 11.8% average improvement in dedicated faithfulness metrics over the previous SOTA. Doctors prefer uMedSum’s summaries 6 times more than previous SOTA in difficult cases containing confabulations or missing information. These results highlight uMedSum’s effectiveness and generalizability across various datasets and metrics, marking a significant advancement in clinical summarization. uMedSum toolkit is made available on GitHub.
%R 10.18653/v1/2025.acl-long.134
%U https://aclanthology.org/2025.acl-long.134/
%U https://doi.org/10.18653/v1/2025.acl-long.134
%P 2653-2672
Markdown (Informal)
[uMedSum: A Unified Framework for Clinical Abstractive Summarization](https://aclanthology.org/2025.acl-long.134/) (Nagar et al., ACL 2025)
ACL
- Aishik Nagar, Yutong Liu, Andy T. Liu, Viktor Schlegel, Vijay Prakash Dwivedi, Arun-Kumar Kaliya-Perumal, Guna Pratheep Kalanchiam, Yili Tang, and Robby T. Tan. 2025. uMedSum: A Unified Framework for Clinical Abstractive Summarization. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2653–2672, Vienna, Austria. Association for Computational Linguistics.