Safety-aligned LLMs fail at core therapeutic tasks in simulated prolonged exposure and CBT sessions by grounding patients, offering false reassurance, and refusing to challenge harmful cognitions.
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
-
AI Safety Training Can be Clinically Harmful
Safety-aligned LLMs fail at core therapeutic tasks in simulated prolonged exposure and CBT sessions by grounding patients, offering false reassurance, and refusing to challenge harmful cognitions.