Evaluating Risk Progression in Mental Health Chatbots Using Escalating Prompts
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
The safety of large language models (LLMs) as mental health chatbots is not fully established. This study evaluated the risk escalation responses of publicly available ChatGPT conversational agents when presented with prompts of increasing depression severity and suicidality. The average referral point to a human was at the midpoint of escalating prompts. However, most agents only definitively recommended professional help at the highest level of risk. Few agents included crisis resources like suicide hotlines. The results suggest current LLMs may fail to escalate mental health risk scenarios appropriately. More rigorous testing and oversight are needed before deployment in mental healthcare settings.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The PHQ-9: Validity of a brief depression severity measure
Kroenke, K., Spitzer, R. L., & Williams, J. B. W. (2001) · Journal of General Internal Medicine · doi:10.1046/j.1525-1497.2001.016009606.x · Cited by 44,910
Fitzpatrick, K. K., Darcy, A., & Vierhile, M. (2017) · JMIR Mental Health · doi:10.2196/mental.7785 · Cited by 2,730
Estimating the true global burden of mental illness
Vigo, D., Thornicroft, G., & Atun, R. (2016) · The Lancet Psychiatry · doi:10.1016/s2215-0366(15)00505-2 · Cited by 2,494
Prevalence and Treatment of Mental Disorders, 1990 to 2003
Kessler, R. C., Demler, O., Frank, R. G., Olfson, M., Pincus, H. A., Walters, E. E., Wang, P., Wells, K. B., & Zaslavsky, A. M. (2005) · New England Journal of Medicine · doi:10.1056/nejmsa043266 · Cited by 1,910
Barriers to mental health treatment: results from the WHO World Mental Health surveys
Andrade, L. H., Alonso, J., Mneimneh, Z., Wells, J. E., Al-Hamzawi, A., Borges, G., Bromet, E., Bruffaerts, R., de Girolamo, G., de Graaf, R., et al. (2014) · Psychological Medicine · doi:10.1017/s0033291713001943 · Cited by 1,289 · cited 1×
“Barriers like cost, stigma, insufficient providers, and access difficulties have resulted in unmet needs (4).”
BackgroundAbd-Alrazaq, A. A., Rababeh, A., Alajlani, M., Bewick, B. M., & Househ, M. (2020) · Journal of Medical Internet Research · doi:10.2196/16021 · Cited by 503 · cited 1×
“The safety of using chatbots to deliver mental health services is not established (16).”
BackgroundSharma, A., Lin, I. W., Miner, A. S., Atkins, D. C., & Althoff, T. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-022-00593-2 · Cited by 500
Ethical and social risks of harm from Language Models
Weidinger, L., Mellor, J., Rauh, M., Griffin, C., Uesato, J., Huang, P.-S., Cheng, M., Glaese, M., Balle, B., Kasirzadeh, A., et al. (2021) · arXiv · doi:10.48550/arxiv.2112.04359 · Cited by 477
Xie, Y., Seth, I., Hunter-Smith, D. J., Rozen, W. M., Ross, R., & Lee, M. (2023) · Aesthetic Plastic Surgery · doi:10.1007/s00266-023-03338-7 · Cited by 198 · cited 1×
“This conversational ability makes LLMs promising for mental health counseling (9).”
BackgroundTowards Interpretable Mental Health Analysis with Large Language Models
Yang, K., Ji, S., Zhang, T., Xie, Q., Kuang, Z., & Ananiadou, S. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.370 · Cited by 155
Cited by
The Opportunities and Risks of Large Language Models in Mental Health
Lawrence, H. R., Schneider, R. A., Rubin, S. B., Matarić, M. J., McDuff, D. J., & Jones Bell, M. (2024) · JMIR Mental Health · doi:10.2196/59479 · Cited by 235
Evaluating generative AI responses to real-world drug-related questions
Giorgi, S., Isman, K., Liu, T., Fried, Z., Sedoc, J., & Curtis, B. (2024) · Psychiatry Research · doi:10.1016/j.psychres.2024.116058 · Cited by 24
“…questions are typically taken from varying sources, including healthcare professionals (Bian et al., 2024), patient inquiries (He et al., 2023), social media (Amin et al., 2023), clinical assessments (e.g., PHQ-9) (Hes-ton, 2023), and standard Question/Answer (QA) databases (Singhal et al., 2023).”
Sobowale, K., & Humphrey, D. K. (2025) · JMIR Formative Research · doi:10.2196/65605 · Cited by 15
Kuhail, M. A., Al-Shamaileh, O., Farooq, S., Shahin, H., Abdelzaher, F., & Thomas, J. (2025) · Human Behavior and Emerging Technologies · doi:10.1155/hbe2/9942295 · Cited by 11
A scoping review on the mental health harms of LLM-based chatbots
Diel, A., Torous, J., Cuijpers, P., Kleesiek, J., Nensa, F., Weber, N., Faust, F., Lalgi, T. J., Mellis, F. S., Teufel, M., et al. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-03054-x · Cited by 4
Metadata
- Authors
- Heston, T. F.
- Venue
- medRxiv
- Publisher
- openRxiv
- Published
- 2023-09-12
- OpenAlex
- W4386631823
- Cited by
- 12
- References
- 11
- Type
- posted content
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Evaluating Risk Progression in Mental Health Chatbots Using Escalating Prompts. https://app.cochat.ai/papers/10.1101/2023.09.10.23295321
- The paper
- Heston, T. F. (2023). Evaluating Risk Progression in Mental Health Chatbots Using Escalating Prompts. medRxiv. https://doi.org/10.1101/2023.09.10.23295321
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.