Metraipolis › archive › dc_cbb3e0fb6bb5
From Clinical Judgment to Checkable Rules: Clinician-Led Guardrails for Mental-Health Chatbots — arXiv:2610.30690
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.30690
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T08:34:35.827Z
- SHA-256 of the archived text
b478c6432aed9bdce0676b44b6dcd598fb702eab0e9a90665eb981c992fa2ec2- Stable URL of this page
https://metraipolis.com/documento/dc_cbb3e0fb6bb5
How to cite
From Clinical Judgment to Checkable Rules: Clinician-Led Guardrails for Mental-Health Chatbots — arXiv:2610.30690 — arXiv (en), https://arxiv.org/abs/2610.30690 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbb3e0fb6bb5 (Metraipolis archive dc_cbb3e0fb6bb5, sha256 b478c6432aed9bdce0676b44b6dcd598fb702eab0e9a90665eb981c992fa2ec2)
BibTeX
@misc{dccbb3e0fb6bb5,
title = {From Clinical Judgment to Checkable Rules: Clinician-Led Guardrails for Mental-Health Chatbots — arXiv:2610.30690},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.30690},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbb3e0fb6bb5; sha256 b478c6432aed9bdce0676b44b6dcd598fb702eab0e9a90665eb981c992fa2ec2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30690. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) deployed in mental-health contexts can be evaluated for safety failures, but the resulting judgments are often difficult to inspect or explain. Common approaches to improving safety rely on prompt engineering, LLM-as-a-Judge, and Constitutional AI. In this work, we describe a clinician-led alternative in which two clinicians define, finalize, and adjudicate the four safety checks of a rule base, which is formally verified for internal consistency and applied as a guardrail over LLM outputs. Here and in the title, clinician-led refers to this rule base, not to the fact extractor or the uncertainty default, which are ours. Every verdict of the resulting verification layer is recomputable from a named rule and sixteen facts. Against an LLM judge matched in model, revision, quantization, rule text, and decoding but without the layer's computed 988/911 fact, the largest disagreement class, the satisfied-rule class, is structured: the Llama-3.3-70B judge, on its primary prompt, demands a crisis resource from 55 of the 65 replies (84.6%) that already contain one, while the same model, asked as a fact extractor, reports a recognized resource present on 54 of the 55. The verification layer never raises that demand, by construction. We report with equal prominence where this judge is stronger: fewer false crisis alarms on the one reference-scored check. We also report the measured cost (a specification revision raised block-class outcomes on held-out boundary prompts of an over-refusal benchmark from 6.0% to 16.0%, chiefly by changing fact extraction), the clinicians' decision to keep our uncertainty default, and the analysis of the result. The contribution is not a safer verdict. It is a guardrail whose disagreements with the judge localize to named rules and facts and whose measured costs trace to named facts and the uncertainty default. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2610.30690 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-25T08:31:13.179Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).