Fine-tuning LLMs for Passive Depression Severity Estimation from AI Mental Health Dialogue

• URL: http://arxiv.org/abs/2606.17973v1
• Date: Tue, 16 Jun 2026 14:28:47 GMT
• Title: Fine-tuning LLMs for Passive Depression Severity Estimation from AI Mental Health Dialogue
• Abstract summary: Depression is the leading cause of disability worldwide, and early detection of symptom change is essential for timely intervention.<n>We propose a passive, continuous symptom monitoring in AI mental health platforms without requiring users to complete self-report measures.
• Score: 4.051184721197422
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Depression is the leading cause of disability worldwide, and early detection of symptom change is essential for timely intervention. Validated instruments such as the Patient Health Questionnaire-9 (PHQ-9) support symptom monitoring at scale, but real-world completion rates are low, introducing response bias and systematic missingness. Passive approaches that infer severity from routinely generated data could close this gap. We address this by predicting PHQ-9 total scores directly from transcripts of conversations between users and an AI mental health application, requiring only conversation text and no additional clinical data. We fine-tune a Qwen3.5-27B backbone with a regression head, augment 3,111 ground-truth labels with pseudolabels generated by a reasoning model (Claude Opus) and iteratively trained intermediate models, for a combined dataset of 6,283 users. On a held-out test set of 842 users, our best model achieves MAE = 2.6, RMSE = 4.0, Pearson r = 0.80, and AUC = 0.91 at the PHQ-9 >= 10 clinical threshold. We also find AUC > 0.87 at every severity threshold from PHQ-9 >= 3 to PHQ-9 >= 24, demonstrating that the model captures depression severity across the full clinical spectrum. This work opens the door to passive, continuous symptom monitoring in AI mental health platforms, without requiring users to complete self-report measures.

Related papers

• Post-Operative Glioma Segmentation via Loss Stabilization, Normalization and Subspace Attention [46.03321798937855]
  We show that the standard Generalized Dice Loss (GDL) is unstable under domain shift.<n>We propose a Subspace-Aware Class Attention (SACA) module that re-calibrates the bottleneck features and raises Enhancing Tumor (ET) sensitivity by 8%.
  arXiv  Detail & Related papers  (2026-07-23T09:59:30Z)
• Psych-ECA: A Reproducible Semi-Synthetic Benchmark for Synthetic Control Arms in Longitudinal Psychiatry [0.0]
  External and synthetic control arms (ECAs) are entering psychiatric drug development.<n>Psych-ECA is a fully reproducible generator of longitudinal symptom trajectories for depression, anxiety, and psychosis.<n>We benchmark eight estimators spanning carry-forward, pooled real-world-data averages, nearest-neighbour matching, linear mixed models, gradient boosting, and the Scribe trajectory-bridge method.
  arXiv  Detail & Related papers  (2026-07-07T16:04:16Z)
• Reading between the Lines: Leveraging Large Language Models for Global Dementia and Depression Assessment from Clinical Interviews [17.404708771543188]
  Dementia and depression are the most prevalent neuropsychiatric disorders in geriatric populations.<n>We introduce an observer-based Global Depression Scale (GDS-D) aligned with the established Global Deterioration Scale (GDS)
  arXiv  Detail & Related papers  (2026-06-16T15:01:30Z)
• Predicting Neuromodulation Outcome for Parkinson's Disease with Generative Virtual Brain Model [95.41752463487008]
  Parkinson's disease affects over ten million people worldwide.<n>Inter-individual variability limits empirical treatment selection, increasing non-negligible surgical risk and cost.<n>We bridge this gap with a pretraining-finetuning framework to predict outcomes directly from resting-state fMRI.
  arXiv  Detail & Related papers  (2026-03-31T02:36:10Z)
• Depression Detection at the Point of Care: Automated Analysis of Linguistic Signals from Routine Primary Care Encounters [13.125686189457369]
  Depression is underdiagnosed in primary care, yet timely identification remains critical.<n>We investigated automated depression detection from 1,108 audio-recorded primary care encounters.
  arXiv  Detail & Related papers  (2026-03-11T21:08:55Z)
• DispatchMAS: Fusing taxonomy and artificial intelligence agents for emergency medical services [49.70819009392778]
  Large Language Models (LLMs) and Multi-Agent Systems (MAS) offer opportunities to augment dispatchers.<n>This study aimed to develop and evaluate a taxonomy-grounded, multi-agent system for simulating realistic scenarios.
  arXiv  Detail & Related papers  (2025-10-24T08:01:21Z)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• Development and Evaluation of HopeBot: an LLM-based chatbot for structured and interactive PHQ-9 depression screening [48.355615275247786]
  HopeBot administers the Patient Health Questionnaire-9 (PHQ-9) using retrieval-augmented generation and real-time clarification.<n>In a within-subject study, 132 adults in the United Kingdom and China completed both self-administered and chatbots versions.<n>Overall, 87.1% expressed willingness to reuse or recommend HopeBot.
  arXiv  Detail & Related papers  (2025-07-08T13:41:22Z)
• LLM Assistance for Pediatric Depression [2.1398676192061683]
  This work investigates the feasibility of state-of-the-art LLMs for depressive symptom extraction in pediatric settings (ages 6-24).<n>Our findings show that all LLMs are 60% more efficient than word match, with Flan leading in precision (average F1: 0.65, precision: 0.78), excelling in the extraction of more rare symptoms like "sleep problems" (F1: 0.92) and "self-loathing" (F1: 0.8)<n>Llama 3, with the highest recall (0.90), overgeneralizes symptoms, making it less suitable for this type of analysis.
  arXiv  Detail & Related papers  (2025-01-29T09:27:27Z)
• Enhancing Depression Diagnosis with Chain-of-Thought Prompting [1.8532406942078647]
  We theorize that using chain-of-thought (CoT) prompting to evaluate Patient Health Questionnaire-8 (PHQ-8) scores will improve the accuracy of the scores determined by AI models. Our goal is to expand upon AI models' understanding of the intricacies of human conversation, allowing them to more effectively assess a patient's feelings and tone.
  arXiv  Detail & Related papers  (2024-08-26T07:19:07Z)
• Automatically measuring speech fluency in people with aphasia: first achievements using read-speech data [55.84746218227712]
  This study aims at assessing the relevance of a signalprocessingalgorithm, initially developed in the field of language acquisition, for the automatic measurement of speech fluency.
  arXiv  Detail & Related papers  (2023-08-09T07:51:40Z)
• Exploiting prompt learning with pre-trained language models for Alzheimer's Disease detection [70.86672569101536]
  Early diagnosis of Alzheimer's disease (AD) is crucial in facilitating preventive care and to delay further progression. This paper investigates the use of prompt-based fine-tuning of PLMs that consistently uses AD classification errors as the training objective function.
  arXiv  Detail & Related papers  (2022-10-29T09:18:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.