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

Wykaz prac cytowanych wewnątrz artykułu (relacja cites → Publication), pobrany ze zweryfikowanych metadanych PubMed / Crossref:

1. (WHO, 2025); https://www.who.int/publications/i/item/9789240114487
   pubmed_reference_list
2. Liu, W. et al. Global burden and trends of major mental disorders in individuals under 24 years of age from 1990 to 2021, with projections to 2050: Insights from the Global Burden of Disease Study 2021. , 1635801 (2025).
   pubmed_reference_list
3. Shelmerdine, S. C. et al. AI chatbots and the loneliness crisis. , r2509 (2025).
   pubmed_reference_list
4. McCain, M. et al. How people use Claude for support, advice, and companionship. https://www.anthropic.com/news/how-people-use-claude-for-support-advice-and-companionship (2025).
   pubmed_reference_list
5. Costa-Gomez, B. et al. It’s about time: the Copilot usage report 2025. https://microsoft.ai/news/its-about-time-the-copilot-usage-report-2025/ (2025).
   pubmed_reference_list
6. Li, H. et al. Systematic review and meta-analysis of AI-based conversational agents for promoting mental health and well-being. , 236 (2023).
   pubmed_reference_list
7. Habicht, J. et al. Closing the accessibility gap to mental health treatment with a personalized self-referral chatbot. , 595–602 (2024).
   pubmed_reference_list
8. Maples, B. et al. Loneliness and suicide mitigation for students using GPT3-enabled chatbots. , 4 (2024).
   pubmed_reference_list
9. Grabb, D. et al. Risks from language models for automated mental healthcare: ethics and structure for implementation. Preprint at https://arxiv.org/abs/2406.11852v2 (2024).
   pubmed_reference_list
10. Morrin, H. et al. Delusions by design? How everyday AIs might be fuelling psychosis (and what can be done about it). Preprint at https://osf.io/preprints/psyarxiv/cmy7n_v6 (2025).
    pubmed_reference_list
11. Perlis, R. H. et al. Generative AI use and depressive symptoms among US adults. , e2554820 (2026).
    pubmed_reference_list
12. De Freitas, J. et al. The health risks of generative AI-based wellness apps. , 1269–1275 (2024).
    pubmed_reference_list
13. Protecting the well-being of our users. https://www.anthropic.com/news/protecting-well-being-of-users (2025).
    pubmed_reference_list
14. Pan, J. et al. COMPASS-GH is a consensus roadmap for defining standards for safe, accurate and equitable AI in general health queries. , 162–163 (2026).
    pubmed_reference_list
15. Dohnány, S. et al. Technological folie à deux: feedback loops between AI chatbots and mental health. , 336–345 (2026).
    pubmed_reference_list
16. Sobowale, K. et al. Evaluating generative AI psychotherapy chatbots used by youth: cross-sectional study. , e79838 (2025).
    pubmed_reference_list
17. Belli, L. et al. VERA-MH concept paper. Preprint at https://arxiv.org/abs/2510.15297v4 (2025).
    pubmed_reference_list
18. Arnaiz-Rodriguez, A. et al. Between help and harm: an evaluation of mental health crisis handling by LLMs. , e88435 (2026).
    pubmed_reference_list
19. Pombal, J. et al. MindEval: benchmarking language models on multi-turn mental health support. Preprint at https://arxiv.org/abs/2511.18491v3 (2025).
    pubmed_reference_list
20. Yeung, J. A. et al. The psychogenic machine: simulating AI psychosis, delusion reinforcement and harm enablement in large language models. Preprint at https://arxiv.org/abs/2509.10970v2 (2025).
    pubmed_reference_list
21. Luo, H. et al. DialogGuard: multi-agent psychosocial safety evaluation of sensitive LLM responses. Preprint at https://arxiv.org/abs/2512.02282v1 (2025).
    pubmed_reference_list
22. Golden, A. et al. The framework for AI tool assessment in mental health (FAITA - mental health): a scale for evaluating AI-powered mental health tools. , 444–445 (2024).
    pubmed_reference_list
23. Hong, J. et al. Measuring sycophancy of language models in multi-turn dialogues. Preprint at https://arxiv.org/abs/2505.23840v4 (2025).
    pubmed_reference_list
24. Laban, P. et al. LLMs get lost in multi-turn conversation. Preprint at https://arxiv.org/abs/2505.06120v1 (2025).
    pubmed_reference_list
25. Li, Y. et al. CounselBench: a large-scale expert evaluation and adversarial benchmarking of large language models in mental health question answering. Preprint at https://arxiv.org/abs/2506.08584v4 (2025).
    pubmed_reference_list
26. Badawi, A. et al. When can we trust LLMs in mental health? Large-scale benchmarks for reliable LLM evaluation. Preprint at https://arxiv.org/abs/2510.19032v1 (2025).
    pubmed_reference_list
27. Ott, S. et al. Mapping global dynamics of benchmark creation and saturation in artificial intelligence. , 6793 (2022).
    pubmed_reference_list
28. Stamatis, C. A. et al. Beyond simulations: what 20,000 real conversations reveal about mental health AI safety. Preprint at https://arxiv.org/abs/2601.17003v1 (2026).
    pubmed_reference_list
29. Strengthening ChatGPT’s responses in sensitive conversations. https://openai.com/index/strengthening-chatgpt-responses-in-sensitive-conversations/ (2025).
    pubmed_reference_list
30. Samvelyan, M. et al. Rainbow teaming: open-ended generation of diverse adversarial prompts. Preprint at https://arxiv.org/abs/2402.16822v3 (2024).
    pubmed_reference_list
31. Phang, J. et al. Investigating affective use and emotional well-being on ChatGPT. Preprint at https://arxiv.org/abs/2504.03888v1 (2025).
    pubmed_reference_list
32. Kirk, H. R. et al. The benefits, risks and bounds of personalizing the alignment of large language models to individuals. , 383–392 (2024).
    pubmed_reference_list
33. Cheng, M. et al. Sycophantic AI decreases prosocial intentions and promotes dependence. , eaec8352 (2026).
    pubmed_reference_list
34. Inspect AI: framework for large language model evaluations. https://github.com/UKGovernmentBEIS/inspect_ai (2024).
    pubmed_reference_list
35. Gupta, I. et al. Bloom: an open source tool for automated behavioral evaluations. https://alignment.anthropic.com/2025/bloom-auto-evals/ (2025).
    pubmed_reference_list
36. Fronsdal, K. et al. Petri: an open-source auditing tool to accelerate AI safety research. https://www.anthropic.com/research/petri-open-source-auditing (2025).
    pubmed_reference_list
37. Perlis, R. H. et al. STELLA: safety testing engine for large language assistants. Preprint at 10.64898/2025.12.11.25342078 (2025). DOI: 10.64898/2025.12.11.25342078
    pubmed_reference_list
38. Kotov, R. et al. A paradigm shift in psychiatric classification: the hierarchical taxonomy of psychopathology (HiTOP). , 24–25 (2018).
    pubmed_reference_list
39. Beck, A. T. The evolution of the cognitive model of depression and its neurobiological correlates. , 969–977 (2008).
    pubmed_reference_list
40. Salkovskis, P. M. Understanding and treating obsessive-compulsive disorder. , S29–S52 (1999).
    pubmed_reference_list
41. Johnson, S. L. Mania and dysregulation in goal pursuit: a review. , 241–262 (2005).
    pubmed_reference_list
42. Mikulincer, M. et al. Attachment orientations and emotion regulation. , 6–10 (2019).
    pubmed_reference_list
43. Harvey, A. et al. (Oxford Univ. Press, 2004).
    pubmed_reference_list
44. Zhang, C. et al. CPsyCoun: a report-based multi-turn dialogue reconstruction and evaluation framework for Chinese psychological counseling. Preprint at https://arxiv.org/abs/2405.16433v3 (2024).
    pubmed_reference_list
45. Moore, J. et al. Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers. In (eds Wortman Vaughan, J. et al.) 599–627 (Association for Computing Machinery, 2025).
    pubmed_reference_list
46. Siddals, S. et al. ‘It happened to be the perfect thing’: experiences of generative AI chatbots for mental health. , 48 (2024).
    pubmed_reference_list
47. Fang, C. M. et al. How AI and human behaviors shape psychosocial effects of extended chatbot use: a longitudinal randomized controlled study. Preprint at https://arxiv.org/abs/2503.17473v2 (2025).
    pubmed_reference_list
48. Qiu, J. et al. EmoAgent: assessing and safeguarding human-AI interaction for mental health safety. Preprint at https://arxiv.org/abs/2504.09689v3 (2025).
    pubmed_reference_list
49. Sharma, M. et al. Who’s in charge? Disempowerment patterns in real-world LLM usage. Preprint at https://arxiv.org/abs/2601.19062v1 (2026).
    pubmed_reference_list
50. Lawrence, H. R. et al. The opportunities and risks of large language models in mental health. , e59479 (2024).
    pubmed_reference_list
51. Rousmaniere, T. et al. Large language models as mental health providers. , 7–9 (2025).
    pubmed_reference_list
52. Glickman, M. et al. How human–AI feedback loops alter human perceptual, emotional and social judgements. , 345–359 (2025).
    pubmed_reference_list
53. Ibrahim, L. et al. Training language models to be warm can reduce accuracy and increase sycophancy. , 1159–1165 (2026).
    pubmed_reference_list
54. Betley, J. et al. Training large language models on narrow tasks can lead to broad misalignment. , 584–589 (2026).
    pubmed_reference_list
55. Chen, R. et al. Persona vectors: monitoring and controlling character traits in language models. Preprint at https://arxiv.org/abs/2507.21509v3 (2025).
    pubmed_reference_list
56. Kumar, A. et al. When large language models are reliable for judging empathic communication. , 173–185 (2026).
    pubmed_reference_list
57. Zheng, L. et al. Judging LLM-as-a-judge with MT-bench and chatbot arena. Preprint at https://arxiv.org/abs/2306.05685v4 (2023).
    pubmed_reference_list
58. Zhang, M. et al. Preference learning unlocks LLMs’ psycho-counseling skills. Preprint at https://arxiv.org/abs/2502.19731v2 (2025).
    pubmed_reference_list
59. Omar, M. et al. New model, old risks: sociodemographic bias and adversarial hallucinations vulnerability in GPT-5. , 282 (2026).
    pubmed_reference_list
60. Park, J. S. et al. LLM agents grounded in self-reports enable general-purpose simulation of individuals. Preprint at https://arxiv.org/abs/2411.10109v3 (2024).
    pubmed_reference_list
61. Weilnhammer, V. et al. SIM-VAIL: Zenodo release. 10.5281/zenodo.21208170 (2026). DOI: 10.5281/zenodo.21208170
    pubmed_reference_list

Dokładne dopasowania identyfikatorów

Nie znaleziono dopasowań w tej grupie.

Kandydaci do ręcznej kontroli

Nie znaleziono dopasowań w tej grupie.

Konflikty

Nie znaleziono dopasowań w tej grupie.

Podobieństwo nie scala rekordów i nie potwierdza tożsamości publikacji.

Zakres: jawne relacje claims[].source_ids[] powiązane z publikacją.