Fine-tuned Qwen3.5-27B model predicts PHQ-9 scores from AI mental health dialogue transcripts with MAE 2.6, Pearson r 0.80, and AUC 0.91 on held-out test set of 842 users.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fine-tuning LLMs for Passive Depression Severity Estimation from AI Mental Health Dialogue
Fine-tuned Qwen3.5-27B model predicts PHQ-9 scores from AI mental health dialogue transcripts with MAE 2.6, Pearson r 0.80, and AUC 0.91 on held-out test set of 842 users.