Depression Severity Estimation

Follow this topic Ask about this topic

Depression severity estimation aims to measure symptom levels for screening, clinical decision support, and tracking change over time, often against scales such as the PHQ-8/9 or MADRS. Approaches range from statistical models of questionnaire and behavioral features to machine learning on speech, text, video, and wearable data, as well as large language models that score interviews or conversations; multimodal fusion and symptom-guided attention are common strategies. Evaluation uses clinical interview datasets and benchmarks such as DAIC-WOZ and AVEC, but performance can shift across languages, populations, interview protocols, and assessment scales. A central tension is that strong agreement with labels does not by itself establish clinical validity: calibration, evidence faithfulness, cross-context generalization, and reliable measurement of change remain open challenges.

Latest papers

35 papers9 papers in the last four weeks, up 80% on the four weeks before. 0.1% of all new papers.

Language Shapes Mental Health Evaluations in Large Language Models
Mar 6, 2026Jiayi Xu, Xiyang HuCross-Lingual Consistency in Language Models Multilingual Language Model Evaluation
University of North Carolina at Chapel Hill · Arizona State University
Clinically Inspired Symptom-Guided Depression Detection from Emotion-Aware Speech Representations
Feb 17, 2026Chaithra Nerella, Chiranjeevi YarraDepression Severity Estimation Clinical Speech Processing
Speech Processing Lab, LTRC IIIT Hyderabad Hyderabad, India
"Mirror" Large Language Model Evaluations of Depression are Criterion Contaminated
Aug 7, 2025Tong Li, Rasiq Hussain, Mehak Gupta +1Depression Detection Mental Health
Division of Computational & Data Sciences (DCDS), Washington University in St. Louis, St. Louis, MO · Department of Computer Science, SMU · Department of Psychological & Brain Sciences, Washington University in St. Louis
Leveraging LLMs for Translating and Classifying Mental Health Data
Oct 16, 2024Konstantinos Skianis, A. Seza Doğruöz, John PavlopoulosDepression Severity Estimation Clinical NLP
Department of Computer Science and Engineering, University of Ioannina, Greece · LT3, IDLab, Universiteit Gent, Belgium · Department of Informatics, Athens University of Economics and Business, Greece +1
Building Multilingual Datasets for Predicting Mental Health Severity through LLMs: Prospects and Challenges
Sep 25, 2024Konstantinos Skianis, John Pavlopoulos, A. Seza DoğruözMultilingual Language Model Evaluation Clinical Language Model Evaluation
Department of Computer Science and Engineering, University of Ioannina, Greece · Department of Informatics, Athens University of Economics and Business, Greece · Archimedes/AthenaRC, Greece +1

Mar 6, 2026J/K move · Enter open · S save

Language Shapes Mental Health Evaluations in Large Language Models

Jiayi Xu, Xiyang Hu

University of North Carolina at Chapel Hill · Arizona State University

Cross-Lingual Consistency in Language Models Multilingual Language Model Evaluation Clinical Language Model Evaluation Depression Severity Estimation

Open paper AskPDF arXiv

Multilingual large language models (LLMs) are increasingly used in socially sensitive mental health contexts, including support chatbots, screening, and content moderation. This raises a reliability question: do semantically equivalent mental health inputs elicit comparable evaluations across languages, or systematic shifts consistent with language-associated social and cultural contexts? We examine this question in an English-Chinese setting with GPT-4o and Qwen3-32B using a two-level framework: construct-level evaluative orientation, measured by psychometric stigma instruments, and decision-level behavior, measured by binary stigma detection and four-class depression severity classification. Across instruments and models, Chinese prompts elicit higher stigma-related scores than English prompts. At the decision level, Chinese prompts reduce sensitivity to stigmatizing content and produce more conservative depression severity judgments, leading to more under-estimation errors. These findings show that prompt language can shift both evaluative orientation and downstream behavior in LLM-based mental health evaluation. They highlight the need to evaluate multilingual LLMs not only for aggregate performance, but also for whether they apply comparable evaluative standards across languages in socially sensitive domains.

Latest papers

Language Shapes Mental Health Evaluations in Large Language Models

Clinically Inspired Symptom-Guided Depression Detection from Emotion-Aware Speech Representations

"Mirror" Large Language Model Evaluations of Depression are Criterion Contaminated

Leveraging LLMs for Translating and Classifying Mental Health Data

Building Multilingual Datasets for Predicting Mental Health Severity through LLMs: Prospects and Challenges