Phi-4 and Gemma-2-9B maintain high intra-model consistency (ICC > 0.89) and ASR robustness for HADS scoring while Llama-3.1-8B degrades sharply, with all models showing score-evidence dissociation.
Explainable artificial intelligence for mental health through transparency and interpretability for understandability
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
-
Can We Trust LLMs for Mental Health Screening? Consistency, ASR Robustness, and Evidence Faithfulness
Phi-4 and Gemma-2-9B maintain high intra-model consistency (ICC > 0.89) and ASR robustness for HADS scoring while Llama-3.1-8B degrades sharply, with all models showing score-evidence dissociation.