pith. sign in

Scoping review of 132 studies following PRISMA-ScR guidelines

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

AI Safety Training Can be Clinically Harmful

cs.CL · 2026-04-25 · unverdicted · novelty 6.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • AI Safety Training Can be Clinically Harmful cs.CL · 2026-04-25 · unverdicted · none · ref 4

    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.