@inproceedings{zhou-etal-2025-feedback,
title = "From Feedback to Checklists: Grounded Evaluation of {AI}-Generated Clinical Notes",
author = "Zhou, Karen and
Giorgi, John Michael and
Mani, Pranav and
Xu, Peng and
Liang, Davis and
Tan, Chenhao",
editor = "Potdar, Saloni and
Rojas-Barahona, Lina and
Montella, Sebastien",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2025",
address = "Suzhou (China)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-industry.104/",
pages = "1485--1499",
ISBN = "979-8-89176-333-3",
abstract = "AI-generated clinical notes are increasingly used in healthcare, but evaluating their quality remains a challenge due to high subjectivity and limited scalability of expert review. Existing automated metrics often fail to align with real-world physician preferences. To address this, we propose a pipeline that systematically distills real user feedback into structured checklists for note evaluation. These checklists are designed to be interpretable, grounded in human feedback, and enforceable by LLM-based evaluators. Using deidentified data from over 21,000 clinical encounters (prepared in accordance with the HIPAA safe harbor standard) from a deployed AI medical scribe system, we show that our feedback-derived checklist outperforms a baseline approach in our offline evaluations in coverage, diversity, and predictive power for human ratings. Extensive experiments confirm the checklist{'}s robustness to quality-degrading perturbations, significant alignment with clinician preferences, and practical value as an evaluation methodology. In offline research settings, our checklist offers a practical tool for flagging notes that may fall short of our defined quality standards."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2025-feedback">
<titleInfo>
<title>From Feedback to Checklists: Grounded Evaluation of AI-Generated Clinical Notes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">Michael</namePart>
<namePart type="family">Giorgi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranav</namePart>
<namePart type="family">Mani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davis</namePart>
<namePart type="family">Liang</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>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</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">979-8-89176-333-3</identifier>
</relatedItem>
<abstract>AI-generated clinical notes are increasingly used in healthcare, but evaluating their quality remains a challenge due to high subjectivity and limited scalability of expert review. Existing automated metrics often fail to align with real-world physician preferences. To address this, we propose a pipeline that systematically distills real user feedback into structured checklists for note evaluation. These checklists are designed to be interpretable, grounded in human feedback, and enforceable by LLM-based evaluators. Using deidentified data from over 21,000 clinical encounters (prepared in accordance with the HIPAA safe harbor standard) from a deployed AI medical scribe system, we show that our feedback-derived checklist outperforms a baseline approach in our offline evaluations in coverage, diversity, and predictive power for human ratings. Extensive experiments confirm the checklist’s robustness to quality-degrading perturbations, significant alignment with clinician preferences, and practical value as an evaluation methodology. In offline research settings, our checklist offers a practical tool for flagging notes that may fall short of our defined quality standards.</abstract>
<identifier type="citekey">zhou-etal-2025-feedback</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.104/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>1485</start>
<end>1499</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Feedback to Checklists: Grounded Evaluation of AI-Generated Clinical Notes
%A Zhou, Karen
%A Giorgi, John Michael
%A Mani, Pranav
%A Xu, Peng
%A Liang, Davis
%A Tan, Chenhao
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F zhou-etal-2025-feedback
%X AI-generated clinical notes are increasingly used in healthcare, but evaluating their quality remains a challenge due to high subjectivity and limited scalability of expert review. Existing automated metrics often fail to align with real-world physician preferences. To address this, we propose a pipeline that systematically distills real user feedback into structured checklists for note evaluation. These checklists are designed to be interpretable, grounded in human feedback, and enforceable by LLM-based evaluators. Using deidentified data from over 21,000 clinical encounters (prepared in accordance with the HIPAA safe harbor standard) from a deployed AI medical scribe system, we show that our feedback-derived checklist outperforms a baseline approach in our offline evaluations in coverage, diversity, and predictive power for human ratings. Extensive experiments confirm the checklist’s robustness to quality-degrading perturbations, significant alignment with clinician preferences, and practical value as an evaluation methodology. In offline research settings, our checklist offers a practical tool for flagging notes that may fall short of our defined quality standards.
%U https://aclanthology.org/2025.emnlp-industry.104/
%P 1485-1499
Markdown (Informal)
[From Feedback to Checklists: Grounded Evaluation of AI-Generated Clinical Notes](https://aclanthology.org/2025.emnlp-industry.104/) (Zhou et al., EMNLP 2025)
ACL