A subtask decomposition of depression detection shows LLMs are biased by explicit depression keywords, and DPO fine-tuning on quality-filtered machine-generated rationales improves joint PHQ-9 labeling on the hardest samples.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Systematic Evaluation of Machine-Generated Reasoning and PHQ-9 Labeling for Depression Detection Using Large Language Models
A subtask decomposition of depression detection shows LLMs are biased by explicit depression keywords, and DPO fine-tuning on quality-filtered machine-generated rationales improves joint PHQ-9 labeling on the hardest samples.