Metraipolis › archive › dc_2fc74815ded1

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

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.21253
License (as archived): CC0-1.0
Archived: 2026-10-16T09:12:04.007Z
SHA-256 of the archived text: 9dcfc047d8b4fd199638b605c173428a3f3996e755dbc13fdceaace39de6ba16
Stable URL of this page: https://metraipolis.com/documento/dc_2fc74815ded1

How to cite

What do AI chatbots do after users decline therapeutic redirection for suicide thoughts? — arXiv:2610.21253 — arXiv (en), https://arxiv.org/abs/2610.21253 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2fc74815ded1 (Metraipolis archive dc_2fc74815ded1, sha256 9dcfc047d8b4fd199638b605c173428a3f3996e755dbc13fdceaace39de6ba16)

BibTeX

@misc{dc2fc74815ded1,
  title = {What do AI chatbots do after users decline therapeutic redirection for suicide thoughts? — arXiv:2610.21253},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21253},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2fc74815ded1; sha256 9dcfc047d8b4fd199638b605c173428a3f3996e755dbc13fdceaace39de6ba16},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), 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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2610.21253 — 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 2026-10-16T08:44:17.925Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).