ProMind-LLM integrates objective sensor data and subjective mental records via domain-specific training, self-refine formatting, and causal chain-of-thought prompting to improve LLM mental health risk classification.
We use a learn- ing rate warmup of 5 % of the total training steps, followed by cosine annealing of the learning rate, the maximum learning rate during this period is 5 × 10−5
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ProMind-LLM: Proactive Mental Health Care via Causal Reasoning with Sensor Data
ProMind-LLM integrates objective sensor data and subjective mental records via domain-specific training, self-refine formatting, and causal chain-of-thought prompting to improve LLM mental health risk classification.