Medical chatbots frequently give actionable medication guidance in later turns of a conversation even after refusing the same help on the first turn, so first-turn safety checks miss most unsafe outcomes.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
TAF-MED: Multi-Turn Safety Refusal Collapse in LLMs Under Declared Self-Treatment Intent
Medical chatbots frequently give actionable medication guidance in later turns of a conversation even after refusing the same help on the first turn, so first-turn safety checks miss most unsafe outcomes.