@inproceedings{shah-etal-2025-tn,
title = "{TN}-Eval: Rubric and Evaluation Protocols for Measuring the Quality of Behavioral Therapy Notes",
author = "Shah, Raj Sanjay and
Xu, Lei and
Liu, Qianchu and
Burnsky, Jon and
Bertagnolli, Andrew and
Shivade, Chaitanya",
editor = "Rehm, Georg and
Li, Yunyao",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-industry.14/",
doi = "10.18653/v1/2025.acl-industry.14",
pages = "179--199",
ISBN = "979-8-89176-288-6",
abstract = "Behavioral therapy notes are important for both legal compliance and patient care. Unlike progress notes in physical health, quality standards for behavioral therapy notes remain underdeveloped. To address this gap, we collaborated with licensed therapists to design a comprehensive rubric for evaluating therapy notes across key dimensions: completeness, conciseness, and faithfulness. Further, we extend a public dataset of behavioral health conversations with therapist-written notes and LLM-generated notes, and apply our evaluation framework to measure their quality. We find that: (1) A rubric-based manual evaluation protocol offers more reliable and interpretable results than traditional Likert-scale annotations. (2) LLMs can mimic human evaluators in assessing completeness and conciseness but struggle with faithfulness. (3) Therapist-written notes often lack completeness and conciseness, while LLM-generated notes contain hallucinations. Surprisingly, in a blind test, therapists prefer and judge LLM-generated notes to be superior to therapist-written notes. As recruiting therapists for annotation is expensive, we will release the rubric, therapist-written notes, and expert annotations to support future research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shah-etal-2025-tn">
<titleInfo>
<title>TN-Eval: Rubric and Evaluation Protocols for Measuring the Quality of Behavioral Therapy Notes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="given">Sanjay</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianchu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jon</namePart>
<namePart type="family">Burnsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Bertagnolli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaitanya</namePart>
<namePart type="family">Shivade</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 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</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">979-8-89176-288-6</identifier>
</relatedItem>
<abstract>Behavioral therapy notes are important for both legal compliance and patient care. Unlike progress notes in physical health, quality standards for behavioral therapy notes remain underdeveloped. To address this gap, we collaborated with licensed therapists to design a comprehensive rubric for evaluating therapy notes across key dimensions: completeness, conciseness, and faithfulness. Further, we extend a public dataset of behavioral health conversations with therapist-written notes and LLM-generated notes, and apply our evaluation framework to measure their quality. We find that: (1) A rubric-based manual evaluation protocol offers more reliable and interpretable results than traditional Likert-scale annotations. (2) LLMs can mimic human evaluators in assessing completeness and conciseness but struggle with faithfulness. (3) Therapist-written notes often lack completeness and conciseness, while LLM-generated notes contain hallucinations. Surprisingly, in a blind test, therapists prefer and judge LLM-generated notes to be superior to therapist-written notes. As recruiting therapists for annotation is expensive, we will release the rubric, therapist-written notes, and expert annotations to support future research.</abstract>
<identifier type="citekey">shah-etal-2025-tn</identifier>
<identifier type="doi">10.18653/v1/2025.acl-industry.14</identifier>
<location>
<url>https://aclanthology.org/2025.acl-industry.14/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>179</start>
<end>199</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TN-Eval: Rubric and Evaluation Protocols for Measuring the Quality of Behavioral Therapy Notes
%A Shah, Raj Sanjay
%A Xu, Lei
%A Liu, Qianchu
%A Burnsky, Jon
%A Bertagnolli, Andrew
%A Shivade, Chaitanya
%Y Rehm, Georg
%Y Li, Yunyao
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-288-6
%F shah-etal-2025-tn
%X Behavioral therapy notes are important for both legal compliance and patient care. Unlike progress notes in physical health, quality standards for behavioral therapy notes remain underdeveloped. To address this gap, we collaborated with licensed therapists to design a comprehensive rubric for evaluating therapy notes across key dimensions: completeness, conciseness, and faithfulness. Further, we extend a public dataset of behavioral health conversations with therapist-written notes and LLM-generated notes, and apply our evaluation framework to measure their quality. We find that: (1) A rubric-based manual evaluation protocol offers more reliable and interpretable results than traditional Likert-scale annotations. (2) LLMs can mimic human evaluators in assessing completeness and conciseness but struggle with faithfulness. (3) Therapist-written notes often lack completeness and conciseness, while LLM-generated notes contain hallucinations. Surprisingly, in a blind test, therapists prefer and judge LLM-generated notes to be superior to therapist-written notes. As recruiting therapists for annotation is expensive, we will release the rubric, therapist-written notes, and expert annotations to support future research.
%R 10.18653/v1/2025.acl-industry.14
%U https://aclanthology.org/2025.acl-industry.14/
%U https://doi.org/10.18653/v1/2025.acl-industry.14
%P 179-199
Markdown (Informal)
[TN-Eval: Rubric and Evaluation Protocols for Measuring the Quality of Behavioral Therapy Notes](https://aclanthology.org/2025.acl-industry.14/) (Shah et al., ACL 2025)
ACL