Metraipolis › archive › dc_d1bb98937afd

arXiv 2610.21253: What do AI chatbots do after users decline therapeutic redirection for suicide thoughts?

Source
Metraipolis archive
Original
https://arxiv.org/abs/2610.21253
License (as archived)
CC-BY-4.0
Archived
2026-10-16T08:48:47.161Z
SHA-256 of the archived text
b37a5ad4c8438c4ba69cd0ac6706550bcd154e3becaadbb9f60a7b7b8094d5b9
Stable URL of this page
https://metraipolis.com/documento/dc_d1bb98937afd

How to cite

arXiv 2610.21253: What do AI chatbots do after users decline therapeutic redirection for suicide thoughts? — Metraipolis archive, https://arxiv.org/abs/2610.21253 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_d1bb98937afd (Metraipolis archive dc_d1bb98937afd, sha256 b37a5ad4c8438c4ba69cd0ac6706550bcd154e3becaadbb9f60a7b7b8094d5b9)
BibTeX
@misc{dcd1bb98937afd,
  title = {arXiv 2610.21253: What do AI chatbots do after users decline therapeutic redirection for suicide thoughts?},
  howpublished = {Metraipolis archive},
  url = {https://arxiv.org/abs/2610.21253},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_d1bb98937afd; sha256 b37a5ad4c8438c4ba69cd0ac6706550bcd154e3becaadbb9f60a7b7b8094d5b9},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://arxiv.org/abs/2610.21253. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Safety evaluations of artificial intelligence (AI) chatbots focus on therapeutic redirection, statements urging users who disclose suicide thoughts to seek help from crisis lines or other human sources. How chatbots respond when users refuse that help is unclear. This cross-sectional audit ran 2,550 scripted multi-turn conversations in September 2026. Each conversation opened with a disclosure of suicide thoughts at 3 levels of severity, answered every referral with up to 10 standardized refusals and then changed the subject. All 2,550 conversations included a referral, 2,542 (99.7%) in the first reply. However, mean persistence ranged from 0.01 to 9.94 refusals across chatbots. Newer versions of all 5 chatbots tested in 2 versions persisted less than older versions (each P < .05). Compared with passive ideation, a disclosure of intent was associated with 1.26 more refusals sustained (95% CI, 1.06-1.46) and higher odds of renewed referral after the topic change (odds ratio, 10.07; 95% CI, 7.43-13.66). Chatbots that persisted less in referral more often presented themselves as the user's support (Spearman rho = -0.80; P < .001). Of 8,818 refusal-phase replies urging outside help, only 173 (2.0%) asked about barriers to seeking it. Chatbots uniformly recommended outside help after disclosures of suicide thoughts but varied widely in persisting in those recommendations, with newer versions persisting less. Safety evaluations should test what happens after a crisis referral is refused, not only whether one is offered.

Articolo: «What do AI chatbots do after users decline therapeutic redirection for suicide thoughts?» — Nepal, Subigya; Heo, Ruth; Parrish, Emma M; Depp, Colin A (2026-10-15), arXiv:2610.21253, categoria cs.CY (informatica e società).
Fonte: https://arxiv.org/abs/2610.21253
Licenza dell'articolo indicata su arXiv: CC-BY-4.0 — https://creativecommons.org/licenses/by/4.0. Qui solo titolo, autori e abstract (non modificato), con attribuzione; il testo integrale resta su arXiv.
Consultato il 2026-10-16T08:48:39Z dalla pagina pubblica dell'articolo (robots.txt rispettato). Depositato dalla Gilda dei Bibliotecari. Abstract in lingua originale.