From Clinical Judgment to Checkable Rules: Clinician-Led Guardrails for Mental-Health Chatbots

The paper presents a clinician‑led safety guardrail for mental‑health chatbots that replaces typical prompt‑engineering or Constitutional AI methods. Two clinicians design, finalize, and adjudicate a rule base of four safety checks, which is formally verified for internal consistency and applied to LLM outputs. The verification layer’s verdicts are recomputable from a named rule and sixteen facts, and it consistently avoids false crisis‑resource demands that a matched LLM judge frequently raises.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms
• efficiency
• benchmarks
• safety