A new benchmark of 1,048 psychiatric notes shows LLMs frequently diagnose too early under incomplete evidence, and safety prompting only trades premature diagnoses for excessive abstention.
hub
Phillips, and Thomas R
1 Pith paper cite this work, alongside 1,005 external citations. Polarity classification is still indexing.
1
Pith paper citing it
1,005
external citations · OpenAlex
hub tools
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Ask Before You Diagnose: Safe-Psych, a Sequential Evaluation Benchmark for LLMs in Psychiatry
A new benchmark of 1,048 psychiatric notes shows LLMs frequently diagnose too early under incomplete evidence, and safety prompting only trades premature diagnoses for excessive abstention.