@inproceedings{xu-etal-2025-tinymentalllms,
title = "{T}iny{M}ental{LLM}s Enable Depression Detection in {C}hinese Social Media Texts",
author = "Xu, Jinyuan and
Lan, Tian and
Valette, Mathieu and
Magistry, Pierre and
Li, Lei",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.157/",
pages = "1352--1363",
abstract = "Depression remains a major global mental health concern, bringing a higher risk of suicide and growing social costs tied to mental disorders. Leveraging social media as a valuable source of emotional signals, we identify two limitations in current NLP-based depression detection frameworks: (1) prediction systems often lack clear, user-friendly explanations for predictions in Depression Detection, and (2) the computational and confidentiality demands of LLMs are misaligned with the need for dependable, privacy-focused small-scale deployments. To address these challenges, we introduce TinyMentalLLMs (TMLs), a compact framework that offers two key contributions: (a) the construction of a small yet representative dataset through psychology-based textometry, and (b) an efficient fine-tuning strategy centered on multiple aspects of depression. This design improves both accuracy and F1 scores in generative models with 0.5B and 1.5B parameters, consistently yielding over 20{\%} performance gains across datasets. TMLs achieve results on par with, and deliver better text quality than, much larger state-of-the-art models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2025-tinymentalllms">
<titleInfo>
<title>TinyMentalLLMs Enable Depression Detection in Chinese Social Media Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinyuan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tian</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Valette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Magistry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Depression remains a major global mental health concern, bringing a higher risk of suicide and growing social costs tied to mental disorders. Leveraging social media as a valuable source of emotional signals, we identify two limitations in current NLP-based depression detection frameworks: (1) prediction systems often lack clear, user-friendly explanations for predictions in Depression Detection, and (2) the computational and confidentiality demands of LLMs are misaligned with the need for dependable, privacy-focused small-scale deployments. To address these challenges, we introduce TinyMentalLLMs (TMLs), a compact framework that offers two key contributions: (a) the construction of a small yet representative dataset through psychology-based textometry, and (b) an efficient fine-tuning strategy centered on multiple aspects of depression. This design improves both accuracy and F1 scores in generative models with 0.5B and 1.5B parameters, consistently yielding over 20% performance gains across datasets. TMLs achieve results on par with, and deliver better text quality than, much larger state-of-the-art models.</abstract>
<identifier type="citekey">xu-etal-2025-tinymentalllms</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.157/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>1352</start>
<end>1363</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TinyMentalLLMs Enable Depression Detection in Chinese Social Media Texts
%A Xu, Jinyuan
%A Lan, Tian
%A Valette, Mathieu
%A Magistry, Pierre
%A Li, Lei
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F xu-etal-2025-tinymentalllms
%X Depression remains a major global mental health concern, bringing a higher risk of suicide and growing social costs tied to mental disorders. Leveraging social media as a valuable source of emotional signals, we identify two limitations in current NLP-based depression detection frameworks: (1) prediction systems often lack clear, user-friendly explanations for predictions in Depression Detection, and (2) the computational and confidentiality demands of LLMs are misaligned with the need for dependable, privacy-focused small-scale deployments. To address these challenges, we introduce TinyMentalLLMs (TMLs), a compact framework that offers two key contributions: (a) the construction of a small yet representative dataset through psychology-based textometry, and (b) an efficient fine-tuning strategy centered on multiple aspects of depression. This design improves both accuracy and F1 scores in generative models with 0.5B and 1.5B parameters, consistently yielding over 20% performance gains across datasets. TMLs achieve results on par with, and deliver better text quality than, much larger state-of-the-art models.
%U https://aclanthology.org/2025.ranlp-1.157/
%P 1352-1363
Markdown (Informal)
[TinyMentalLLMs Enable Depression Detection in Chinese Social Media Texts](https://aclanthology.org/2025.ranlp-1.157/) (Xu et al., RANLP 2025)
ACL
- Jinyuan Xu, Tian Lan, Mathieu Valette, Pierre Magistry, and Lei Li. 2025. TinyMentalLLMs Enable Depression Detection in Chinese Social Media Texts. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 1352–1363, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.