@inproceedings{nguyen-etal-2025-large,
title = "Do Large Language Models Align with Core Mental Health Counseling Competencies?",
author = "Nguyen, Viet Cuong and
Taher, Mohammad and
Hong, Dongwan and
Possobom, Vinicius Konkolics and
Gopalakrishnan, Vibha Thirunellayi and
Raj, Ekta and
Li, Zihang and
Soled, Heather J. and
Birnbaum, Michael L. and
Kumar, Srijan and
De Choudhury, Munmun",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.418/",
doi = "10.18653/v1/2025.findings-naacl.418",
pages = "7488--7511",
ISBN = "979-8-89176-195-7",
abstract = "The rapid evolution of Large Language Models (LLMs) presents a promising solution to the global shortage of mental health professionals. However, their alignment with essential counseling competencies remains underexplored. We introduce CounselingBench, a novel NCMHCE-based benchmark evaluating 22 general-purpose and medical-finetuned LLMs across five key competencies. While frontier models surpass minimum aptitude thresholds, they fall short of expert-level performance, excelling in Intake, Assessment {\&} Diagnosis but struggling with Core Counseling Attributes and Professional Practice {\&} Ethics. Surprisingly, medical LLMs do not outperform generalist models in accuracy, though they provide slightly better justifications while making more context-related errors. These findings highlight the challenges of developing AI for mental health counseling, particularly in competencies requiring empathy and nuanced reasoning. Our results underscore the need for specialized, fine-tuned models aligned with core mental health counseling competencies and supported by human oversight before real-world deployment. Code and data associated with this manuscript can be found at: https://github.com/cuongnguyenx/CounselingBench"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2025-large">
<titleInfo>
<title>Do Large Language Models Align with Core Mental Health Counseling Competencies?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Viet</namePart>
<namePart type="given">Cuong</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Taher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongwan</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinicius</namePart>
<namePart type="given">Konkolics</namePart>
<namePart type="family">Possobom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vibha</namePart>
<namePart type="given">Thirunellayi</namePart>
<namePart type="family">Gopalakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekta</namePart>
<namePart type="family">Raj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heather</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Soled</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Birnbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srijan</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Munmun</namePart>
<namePart type="family">De Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>The rapid evolution of Large Language Models (LLMs) presents a promising solution to the global shortage of mental health professionals. However, their alignment with essential counseling competencies remains underexplored. We introduce CounselingBench, a novel NCMHCE-based benchmark evaluating 22 general-purpose and medical-finetuned LLMs across five key competencies. While frontier models surpass minimum aptitude thresholds, they fall short of expert-level performance, excelling in Intake, Assessment & Diagnosis but struggling with Core Counseling Attributes and Professional Practice & Ethics. Surprisingly, medical LLMs do not outperform generalist models in accuracy, though they provide slightly better justifications while making more context-related errors. These findings highlight the challenges of developing AI for mental health counseling, particularly in competencies requiring empathy and nuanced reasoning. Our results underscore the need for specialized, fine-tuned models aligned with core mental health counseling competencies and supported by human oversight before real-world deployment. Code and data associated with this manuscript can be found at: https://github.com/cuongnguyenx/CounselingBench</abstract>
<identifier type="citekey">nguyen-etal-2025-large</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.418</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.418/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>7488</start>
<end>7511</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Large Language Models Align with Core Mental Health Counseling Competencies?
%A Nguyen, Viet Cuong
%A Taher, Mohammad
%A Hong, Dongwan
%A Possobom, Vinicius Konkolics
%A Gopalakrishnan, Vibha Thirunellayi
%A Raj, Ekta
%A Li, Zihang
%A Soled, Heather J.
%A Birnbaum, Michael L.
%A Kumar, Srijan
%A De Choudhury, Munmun
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F nguyen-etal-2025-large
%X The rapid evolution of Large Language Models (LLMs) presents a promising solution to the global shortage of mental health professionals. However, their alignment with essential counseling competencies remains underexplored. We introduce CounselingBench, a novel NCMHCE-based benchmark evaluating 22 general-purpose and medical-finetuned LLMs across five key competencies. While frontier models surpass minimum aptitude thresholds, they fall short of expert-level performance, excelling in Intake, Assessment & Diagnosis but struggling with Core Counseling Attributes and Professional Practice & Ethics. Surprisingly, medical LLMs do not outperform generalist models in accuracy, though they provide slightly better justifications while making more context-related errors. These findings highlight the challenges of developing AI for mental health counseling, particularly in competencies requiring empathy and nuanced reasoning. Our results underscore the need for specialized, fine-tuned models aligned with core mental health counseling competencies and supported by human oversight before real-world deployment. Code and data associated with this manuscript can be found at: https://github.com/cuongnguyenx/CounselingBench
%R 10.18653/v1/2025.findings-naacl.418
%U https://aclanthology.org/2025.findings-naacl.418/
%U https://doi.org/10.18653/v1/2025.findings-naacl.418
%P 7488-7511
Markdown (Informal)
[Do Large Language Models Align with Core Mental Health Counseling Competencies?](https://aclanthology.org/2025.findings-naacl.418/) (Nguyen et al., Findings 2025)
ACL
- Viet Cuong Nguyen, Mohammad Taher, Dongwan Hong, Vinicius Konkolics Possobom, Vibha Thirunellayi Gopalakrishnan, Ekta Raj, Zihang Li, Heather J. Soled, Michael L. Birnbaum, Srijan Kumar, and Munmun De Choudhury. 2025. Do Large Language Models Align with Core Mental Health Counseling Competencies?. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 7488–7511, Albuquerque, New Mexico. Association for Computational Linguistics.