Simulating Psychological Risks in Human-AI Interactions: Real-Case Informed Modeling of AI-Induced Addiction, Anorexia, Depression, Homicide, Psychosis, and Suicide
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917075602112512 |
|---|---|
| author | Archiwaranguprok, Chayapatr Albrecht, Constanze Maes, Pattie Karahalios, Karrie Pataranutaporn, Pat |
| author_facet | Archiwaranguprok, Chayapatr Albrecht, Constanze Maes, Pattie Karahalios, Karrie Pataranutaporn, Pat |
| contents | As AI systems become increasingly integrated into daily life, their potential to exacerbate or trigger severe psychological harms remains poorly understood and inadequately tested. This paper presents a proactive methodology for systematically exploring psychological risks in simulated human-AI interactions based on documented real-world cases involving AI-induced or AI-exacerbated addiction, anorexia, depression, homicide, psychosis, and suicide. We collected and analyzed 18 reported real-world cases where AI interactions contributed to severe psychological outcomes. From these cases, we developed a process to extract harmful interaction patterns and assess potential risks through 2,160 simulated scenarios using clinical staging models. We tested four major LLMs across multi-turn conversations to identify where psychological risks emerge: which harm domains, conversation stages, and contexts reveal system vulnerabilities. Through the analysis of 157,054 simulated conversation turns, we identify critical gaps in detecting psychological distress, responding appropriately to vulnerable users, and preventing harm escalation. Regression analysis reveals variability across persona types: LLMs tend to perform worse with elderly users but better with low- and middle-income groups compared to high-income groups. Clustering analysis of harmful responses reveals a taxonomy of fifteen distinct failure patterns organized into four categories of AI-enabled harm. This work contributes a novel methodology for identifying psychological risks, empirical evidence of common failure modes across systems, and a classification of harmful AI response patterns in high-stakes human-AI interactions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08880 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Simulating Psychological Risks in Human-AI Interactions: Real-Case Informed Modeling of AI-Induced Addiction, Anorexia, Depression, Homicide, Psychosis, and Suicide Archiwaranguprok, Chayapatr Albrecht, Constanze Maes, Pattie Karahalios, Karrie Pataranutaporn, Pat Human-Computer Interaction As AI systems become increasingly integrated into daily life, their potential to exacerbate or trigger severe psychological harms remains poorly understood and inadequately tested. This paper presents a proactive methodology for systematically exploring psychological risks in simulated human-AI interactions based on documented real-world cases involving AI-induced or AI-exacerbated addiction, anorexia, depression, homicide, psychosis, and suicide. We collected and analyzed 18 reported real-world cases where AI interactions contributed to severe psychological outcomes. From these cases, we developed a process to extract harmful interaction patterns and assess potential risks through 2,160 simulated scenarios using clinical staging models. We tested four major LLMs across multi-turn conversations to identify where psychological risks emerge: which harm domains, conversation stages, and contexts reveal system vulnerabilities. Through the analysis of 157,054 simulated conversation turns, we identify critical gaps in detecting psychological distress, responding appropriately to vulnerable users, and preventing harm escalation. Regression analysis reveals variability across persona types: LLMs tend to perform worse with elderly users but better with low- and middle-income groups compared to high-income groups. Clustering analysis of harmful responses reveals a taxonomy of fifteen distinct failure patterns organized into four categories of AI-enabled harm. This work contributes a novel methodology for identifying psychological risks, empirical evidence of common failure modes across systems, and a classification of harmful AI response patterns in high-stakes human-AI interactions. |
| title | Simulating Psychological Risks in Human-AI Interactions: Real-Case Informed Modeling of AI-Induced Addiction, Anorexia, Depression, Homicide, Psychosis, and Suicide |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2511.08880 |