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

arXiv: https://arxiv.org/abs/2606.17973 · HTML: https://mlsanity.com/paper/2606.17973/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 28 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Builds on (most cited first, 7 of 7)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Revisiting Self-Training for Neural Sequence Generation](https://mlsanity.com/paper/1909.13788/) (2019)
- [AVEC 2019 Workshop and Challenge: State-of-Mind, Detecting Depression with AI, and Cross-Cultural Affect Recognition](https://mlsanity.com/paper/1907.11510/) (2019)
- [DAIC-WOZ: On the Validity of Using the Therapist's prompts in Automatic Depression Detection from Clinical Interviews](https://mlsanity.com/paper/2404.14463/) (2024)
- [DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation](https://mlsanity.com/paper/2512.20773/) (2025)
- [Probabilistic Textual Time Series Depression Detection](https://mlsanity.com/paper/2511.04476/) (2025)

## Built on by (most cited first, 2 of 2)

- [SAGE: Stochastic Prompt Optimization via Agent-Guided Exploration](https://mlsanity.com/paper/2606.18902/) (2026)
- [Optimizing Sparse Outcomes Through Dense Behavioral Signals via Value-Guided Preference Distillation](https://mlsanity.com/paper/2609.14648/) (2026)

## Abstract (arXiv)

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.