@inproceedings{jiang-etal-2025-clear,
title = "{CLEAR}: A Clinically Grounded Tabular Framework for Radiology Report Evaluation",
author = "Jiang, Yuyang and
Chen, Chacha and
Wang, Shengyuan and
Li, Feng and
Tang, Zecong and
Mervak, Benjamin M. and
Chelala, Lydia and
Straus, Christopher M and
Chahine, Reve and
Iii, Samuel G. Armato and
Tan, Chenhao",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.862/",
pages = "15914--15933",
ISBN = "979-8-89176-335-7",
abstract = "Existing metrics often lack the granularity and interpretability to capture nuanced clinical differences between candidate and ground-truth radiology reports, resulting in suboptimal evaluation. We introduce a **Cl**inically grounded tabular framework with **E**xpert-curated labels and **A**ttribute-level comparison for **R**adiology report evaluation (**CLEAR**). CLEAR not only examines whether a report can accurately identify the presence or absence of medical conditions, but it also assesses whether the report can precisely describe each positively identified condition across five key attributes: first occurrence, change, severity, descriptive location, and recommendation. Compared with prior works, CLEAR{'}s multi-dimensional, attribute-level outputs enable a more comprehensive and clinically interpretable evaluation of report quality. Additionally, to measure the clinical alignment of CLEAR, we collaborated with five board-certified radiologists to develop **CLEAR-Bench**, a dataset of 100 chest radiograph reports from MIMIC-CXR, annotated across 6 curated attributes and 13 CheXpert conditions. Our experiments demonstrated that CLEAR achieves high accuracy in extracting clinical attributes and provides automated metrics that are strongly aligned with clinical judgment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2025-clear">
<titleInfo>
<title>CLEAR: A Clinically Grounded Tabular Framework for Radiology Report Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuyang</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chacha</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengyuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zecong</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mervak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lydia</namePart>
<namePart type="family">Chelala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Straus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reve</namePart>
<namePart type="family">Chahine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="given">G</namePart>
<namePart type="given">Armato</namePart>
<namePart type="family">Iii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhao</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>Existing metrics often lack the granularity and interpretability to capture nuanced clinical differences between candidate and ground-truth radiology reports, resulting in suboptimal evaluation. We introduce a **Cl**inically grounded tabular framework with **E**xpert-curated labels and **A**ttribute-level comparison for **R**adiology report evaluation (**CLEAR**). CLEAR not only examines whether a report can accurately identify the presence or absence of medical conditions, but it also assesses whether the report can precisely describe each positively identified condition across five key attributes: first occurrence, change, severity, descriptive location, and recommendation. Compared with prior works, CLEAR’s multi-dimensional, attribute-level outputs enable a more comprehensive and clinically interpretable evaluation of report quality. Additionally, to measure the clinical alignment of CLEAR, we collaborated with five board-certified radiologists to develop **CLEAR-Bench**, a dataset of 100 chest radiograph reports from MIMIC-CXR, annotated across 6 curated attributes and 13 CheXpert conditions. Our experiments demonstrated that CLEAR achieves high accuracy in extracting clinical attributes and provides automated metrics that are strongly aligned with clinical judgment.</abstract>
<identifier type="citekey">jiang-etal-2025-clear</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.862/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>15914</start>
<end>15933</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLEAR: A Clinically Grounded Tabular Framework for Radiology Report Evaluation
%A Jiang, Yuyang
%A Chen, Chacha
%A Wang, Shengyuan
%A Li, Feng
%A Tang, Zecong
%A Mervak, Benjamin M.
%A Chelala, Lydia
%A Straus, Christopher M.
%A Chahine, Reve
%A Iii, Samuel G. Armato
%A Tan, Chenhao
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F jiang-etal-2025-clear
%X Existing metrics often lack the granularity and interpretability to capture nuanced clinical differences between candidate and ground-truth radiology reports, resulting in suboptimal evaluation. We introduce a **Cl**inically grounded tabular framework with **E**xpert-curated labels and **A**ttribute-level comparison for **R**adiology report evaluation (**CLEAR**). CLEAR not only examines whether a report can accurately identify the presence or absence of medical conditions, but it also assesses whether the report can precisely describe each positively identified condition across five key attributes: first occurrence, change, severity, descriptive location, and recommendation. Compared with prior works, CLEAR’s multi-dimensional, attribute-level outputs enable a more comprehensive and clinically interpretable evaluation of report quality. Additionally, to measure the clinical alignment of CLEAR, we collaborated with five board-certified radiologists to develop **CLEAR-Bench**, a dataset of 100 chest radiograph reports from MIMIC-CXR, annotated across 6 curated attributes and 13 CheXpert conditions. Our experiments demonstrated that CLEAR achieves high accuracy in extracting clinical attributes and provides automated metrics that are strongly aligned with clinical judgment.
%U https://aclanthology.org/2025.findings-emnlp.862/
%P 15914-15933
Markdown (Informal)
[CLEAR: A Clinically Grounded Tabular Framework for Radiology Report Evaluation](https://aclanthology.org/2025.findings-emnlp.862/) (Jiang et al., Findings 2025)
ACL
- Yuyang Jiang, Chacha Chen, Shengyuan Wang, Feng Li, Zecong Tang, Benjamin M. Mervak, Lydia Chelala, Christopher M Straus, Reve Chahine, Samuel G. Armato Iii, and Chenhao Tan. 2025. CLEAR: A Clinically Grounded Tabular Framework for Radiology Report Evaluation. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 15914–15933, Suzhou, China. Association for Computational Linguistics.