Evidence mapPaperPMID 42567928Full record

ArticleNature medicine2026

A clinically validated framework for auditing AI chatbot behavior in mental health interactions.

Veith Weilnhammer, Kevin Yc Hou, Lennart Luettgau, Christopher Summerfield, Raymond Dolan, Matthew M Nour

Abstract read
PubMed Publisher
In one paragraph

Article in Nature medicine, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.

0numbers the graph read from it
0cells of the map it votes in
0citing papers in PubMed
field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

0 citing papers in PubMed.

No citing paper in PubMed yet.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

6 authors.

Veith WeilnhammerMax Planck UCL Centre for Computational Psychiatry and Ageing Research, London, UK. v.weilnhammer@ucl.ac.uk.ORCID http://orcid.org/0000-0002-3332-0006
Kevin Yc HouSydney Medical School, University of Sydney, Sydney, Australia.ORCID http://orcid.org/0009-0002-3962-5051
Lennart LuettgauUK AI Security Institute, London, UK.
Christopher SummerfieldUK AI Security Institute, London, UK.
Raymond DolanMax Planck UCL Centre for Computational Psychiatry and Ageing Research, London, UK.
Matthew M NourMax Planck UCL Centre for Computational Psychiatry and Ageing Research, London, UK. matthew.nour@psych.ox.ac.uk.ORCID http://orcid.org/0000-0003-0858-6184

Funding

No grant is acknowledged in the PubMed record.

6 · The paper itself

Abstract

Millions of users turn to consumer artificial intelligence chatbots to discuss emotional, behavioral and mental-health concerns, creating an urgent need for rigorous and scalable safety evaluations. Here we introduce simulated (SIM) vulnerability-amplifying interaction loops (VAILs) (SIM-VAIL), a clinically validated framework for auditing chatbot behavior in mental-health contexts. SIM-VAIL simulates users with specific psychiatric vulnerabilities and conversational intents, engages them in multi-turn conversations with frontier artificial intelligence chatbots (including Claude, ChatGPT, Gemini, Grok and Llama models) and scores each exchange across 13 clinically grounded risk dimensions. Across 810 conversations, spanning 9 target chatbots and 30 simulated user profiles, concerning behavior in target chatbots was widespread, albeit reduced in newer models. Concerning behavior varied by user vulnerability and conversational intent, accumulated over turns, and could be reduced by interventions at early escalation points. Risk was highest when otherwise supportive chatbot behaviors reinforced the psychological mechanisms underlying the simulated user's vulnerability, a pattern we term a VAIL. SIM-VAIL provides a scalable framework for mapping mental-health risk across users, chatbots and conversational trajectories, offering a foundation for targeted safety improvements.

Identifiers

What Socratic holds

Textmetadata
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the Socratic graph.