It Is the Journey, Not the Destination: Moving From End Points to Trajectories When Assessing Chatbot Mental Health Safety
JMIR Mental Health · 2026-04-06 · 13 · e91454-e91454
DOI: 10.2196/91454 ↗At a glance
Journal article in JMIR Mental Health, published online on 2026-04-06. Written by Hamilton Morrin and 4 co-authors. Institution: Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, 16 De Crespigny Park, London, England, SE…. Major MEDLINE topics: Artificial Intelligence, Mental Health. Cited 11 times so far (Crossref); 54 references. The full text is freely available in PubMed Central. Funded by: Wellcome Trust.
Abstract (original language)
Large language models are rapidly becoming embedded in everyday life through artificial intelligence (AI) chatbots that people use for practical assistance and companionship, as well as for support with mental health and emotional well-being. Alongside clear benefits, clinicians and public reports increasingly describe a minority of users whose interactions seem to drift over days or weeks toward strongly questionable convictions, delusions, or suicidal crises. Importantly, clinically meaningful deterioration can occur even without overtly unsafe text outputs, via more insidious processes, such as compulsive use, sleep disruption, withdrawal from human contact, and progressive narrowing of attention around the chatbot relationship. In this Viewpoint, we argue that risk often arises not at a single tipping point but through trajectory effects that accumulate across extended dialogue and that prevailing safety evaluation approaches are misaligned with this reality because they primarily score risk at discrete conversational end points often reached through scripted dialogues lasting just a single turn or several turns. Mental health benchmarks and safety suites (including clinician-informed efforts) have advanced the field by testing refusal behavior, toxicity, and adversarial prompting. However, they often treat the last message as the unit of analysis and, therefore, miss when risk-relevant relational cues, signs of validation, contradiction handling, and shifts in certainty first emerge and how they compound. We propose that mental health safety assessment should shift from end points to trajectories by (1) treating the whole dialogue, not just the end result, as the focus of evaluation; (2) reporting turn-by-turn dynamics, such as delusion confirmation and harm enablement, and timing and persistence of safety interventions; and (3) calibrating short multiturn tests against longer, clinically realistic interaction sequences that can reveal context-length effects and drift . We further argue that transcript-only evaluation is insufficient in mental health contexts. Similar language can reflect very different internal states, and the relationship between expressed psychopathology and real-world harm is nonlinear. Therefore, safety research should incorporate proximal human outcomes following interactions (eg, shifts in certainty, openness to counterevidence, arousal, urge to continue, and subsequent sleep or behavior) and build a prospective clinical surveillance infrastructure that supports transcript donation with consent and linkage to health outcomes. Together, these steps would enable benchmarks that are clinically relevant and better aligned with the types of harms now being observed in real-world chatbot use.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, 16 De Crespigny Park, London, England, SE5 8AB, United Kingdom, 07752 814088.
- Department of Psychological Medicine, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, England, United Kingdom.
- South London and Maudsley NHS Foundation Trust, London, England, United Kingdom.
- King's College Hospital, London, England, United Kingdom.
- Nuraxi AI, London, United Kingdom.
- Department of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, England, United Kingdom.
Funding
- Wellcome Trust
Cite
APA
Morrin, H., Au Yeung, J., Agnew, Z., Østergaard, S. D., & Pollak, T. A. (2026). It Is the Journey, Not the Destination: Moving From End Points to Trajectories When Assessing Chatbot Mental Health Safety. JMIR Mental Health, 13, e91454-e91454. https://doi.org/10.2196/91454
Vancouver
Morrin H, Au Yeung J, Agnew Z, Østergaard SD, Pollak TA. It Is the Journey, Not the Destination: Moving From End Points to Trajectories When Assessing Chatbot Mental Health Safety. JMIR Mental Health. 2026;13:e91454-e91454. doi:10.2196/91454
BibTeX
@article{Morrin2026,
author = {Morrin, Hamilton and Au Yeung, Joshua and Agnew, Zarinah and Østergaard, Søren Dinesen and Pollak, Thomas A},
title = {It Is the Journey, Not the Destination: Moving From End Points to Trajectories When Assessing Chatbot Mental Health Safety},
journal = {JMIR Mental Health},
year = {2026},
volume = {13},
pages = {e91454--e91454},
doi = {10.2196/91454}
}
EUVIMED