The Psychogenic Machine: Simulating AI Psychosis, Delusion Reinforcement and Harm Enablement in Large Language Models

• URL: http://arxiv.org/abs/2509.10970v2
• Date: Wed, 17 Sep 2025 01:44:03 GMT
• Title: The Psychogenic Machine: Simulating AI Psychosis, Delusion Reinforcement and Harm Enablement in Large Language Models
• Authors: Joshua Au Yeung, Jacopo Dalmasso, Luca Foschini, Richard JB Dobson, Zeljko Kraljevic,
• Abstract summary: "AI psychosis" is emerging where user-LLM interactions may exacerbate or induce psychosis or adverse psychological symptoms.<n>Psychosis-bench is a novel benchmark designed to evaluate the psychogenicity of LLMs.<n>We evaluated eight prominent LLMs for Delusion Confirmation, Harm Enablement, and Safety Intervention across explicit and implicit conversational contexts.
• Score: 3.775403046470809
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Background: Emerging reports of "AI psychosis" are on the rise, where user-LLM interactions may exacerbate or induce psychosis or adverse psychological symptoms. Whilst the sycophantic and agreeable nature of LLMs can be beneficial, it becomes a vector for harm by reinforcing delusional beliefs in vulnerable users. Methods: Psychosis-bench is a novel benchmark designed to systematically evaluate the psychogenicity of LLMs comprises 16 structured, 12-turn conversational scenarios simulating the progression of delusional themes(Erotic Delusions, Grandiose/Messianic Delusions, Referential Delusions) and potential harms. We evaluated eight prominent LLMs for Delusion Confirmation (DCS), Harm Enablement (HES), and Safety Intervention(SIS) across explicit and implicit conversational contexts. Findings: Across 1,536 simulated conversation turns, all LLMs demonstrated psychogenic potential, showing a strong tendency to perpetuate rather than challenge delusions (mean DCS of 0.91 $\pm$0.88). Models frequently enabled harmful user requests (mean HES of 0.69 $\pm$0.84) and offered safety interventions in only roughly a third of applicable turns (mean SIS of 0.37 $\pm$0.48). 51 / 128 (39.8%) of scenarios had no safety interventions offered. Performance was significantly worse in implicit scenarios, models were more likely to confirm delusions and enable harm while offering fewer interventions (p < .001). A strong correlation was found between DCS and HES (rs = .77). Model performance varied widely, indicating that safety is not an emergent property of scale alone. Conclusion: This study establishes LLM psychogenicity as a quantifiable risk and underscores the urgent need for re-thinking how we train LLMs. We frame this issue not merely as a technical challenge but as a public health imperative requiring collaboration between developers, policymakers, and healthcare professionals.

Related papers

• Diagnosing Hallucination Risk in AI Surgical Decision-Support: A Sequential Framework for Sequential Validation [5.469454486414467]
  Large language models (LLMs) offer transformative potential for clinical decision support in spine surgery.<n>LLMs pose significant risks through hallucinations, which are factually inconsistent or contextually misaligned outputs.<n>This study introduces a clinician-centered framework to quantify hallucination risks by evaluating diagnostic precision, recommendation quality, reasoning robustness, output coherence, and knowledge alignment.
  arXiv  Detail & Related papers  (2025-11-01T15:25:55Z)
• Independent Clinical Evaluation of General-Purpose LLM Responses to Signals of Suicide Risk [32.17406690566923]
  We introduce findings and methods to facilitate evidence-based discussion about how large language models (LLMs) should behave in response to user signals of risk of suicidal thoughts and behaviors (STB)<n>We find that OLMo-2-32b, and, possibly by extension, other LLMs, will become less likely to invite continued dialog as users send more signals of STB risk in multi-turn settings.
  arXiv  Detail & Related papers  (2025-10-31T14:47:11Z)
• Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL [64.3268313484078]
  Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare.<n>Their ability to produce deceptive outputs, whether intentionally or inadvertently, poses significant safety concerns.<n>We investigate the extent to which LLMs engage in deception within dialogue, and propose the belief misalignment metric to quantify deception.
  arXiv  Detail & Related papers  (2025-10-16T05:29:36Z)
• SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations [47.0190003379175]
  Large Language Models (LLMs) are increasingly deployed in high-risk domains.<n>LLMs often produce hallucinations, raising serious concerns about their reliability.<n>We propose Semantically Equivalent and Coherent Attacks (SECA) to elicit hallucinations.
  arXiv  Detail & Related papers  (2025-10-05T23:44:54Z)
• Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMs [6.0460961868478975]
  We introduce a unified taxonomy of six clinically-informed mental health crisis categories.<n>We benchmark three state-of-the-art LLMs for their ability to classify crisis types and generate safe, appropriate responses.<n>We identify systemic weaknesses in handling indirect or ambiguous risk signals, a reliance on formulaic and inauthentic default replies, and frequent misalignment with user context.
  arXiv  Detail & Related papers  (2025-09-29T14:42:23Z)
• The Problem of Atypicality in LLM-Powered Psychiatry [0.0]
  Large language models (LLMs) are increasingly proposed as scalable solutions to the global mental health crisis.<n>Their deployment in psychiatric contexts raises a distinctive ethical concern: the problem of atypicality.<n>We argue that standard mitigation strategies, such as prompt engineering or fine-tuning, are insufficient to resolve this structural risk.
  arXiv  Detail & Related papers  (2025-08-08T17:36:42Z)
• Beyond Benchmarks: Dynamic, Automatic And Systematic Red-Teaming Agents For Trustworthy Medical Language Models [87.66870367661342]
  Large language models (LLMs) are used in AI applications in healthcare.<n>Red-teaming framework that continuously stress-test LLMs can reveal significant weaknesses in four safety-critical domains.<n>A suite of adversarial agents is applied to autonomously mutate test cases, identify/evolve unsafe-triggering strategies, and evaluate responses.<n>Our framework delivers an evolvable, scalable, and reliable safeguard for the next generation of medical AI.
  arXiv  Detail & Related papers  (2025-07-30T08:44:22Z)
• MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them [52.764019220214344]
  Hallucinations pose critical risks for large language model (LLM)-based agents.<n>We present MIRAGE-Bench, the first unified benchmark for eliciting and evaluating hallucinations in interactive environments.
  arXiv  Detail & Related papers  (2025-07-28T17:38:29Z)
• $\texttt{SAGE}$: A Generic Framework for LLM Safety Evaluation [9.935219917903858]
  This paper introduces the $texttSAGE$ (Safety AI Generic Evaluation) framework.<n>$texttSAGE$ is an automated modular framework designed for customized and dynamic harm evaluations.<n>Our experiments with multi-turn conversational evaluations revealed a concerning finding that harm steadily increases with conversation length.
  arXiv  Detail & Related papers  (2025-04-28T11:01:08Z)
• Benchmarking Chinese Medical LLMs: A Medbench-based Analysis of Performance Gaps and Hierarchical Optimization Strategies [11.0505830548286]
  This study introduces a granular error taxonomy through systematic analysis of top 10 models on MedBench.<n> Evaluation of 10 leading models reveals vulnerabilities, despite achieving 0.86 accuracy in medical knowledge recall.<n>Our analysis uncovers systemic weaknesses in knowledge boundary enforcement and multi-step reasoning.
  arXiv  Detail & Related papers  (2025-03-10T13:28:25Z)
• LLM Internal States Reveal Hallucination Risk Faced With a Query [62.29558761326031]
  Humans have a self-awareness process that allows us to recognize what we don't know when faced with queries. This paper investigates whether Large Language Models can estimate their own hallucination risk before response generation. By a probing estimator, we leverage LLM self-assessment, achieving an average hallucination estimation accuracy of 84.32% at run time.
  arXiv  Detail & Related papers  (2024-07-03T17:08:52Z)
• OR-Bench: An Over-Refusal Benchmark for Large Language Models [65.34666117785179]
  Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs.<n>This study proposes a novel method for automatically generating large-scale over-refusal datasets.<n>We introduce OR-Bench, the first large-scale over-refusal benchmark.
  arXiv  Detail & Related papers  (2024-05-31T15:44:33Z)
• Can AI Relate: Testing Large Language Model Response for Mental Health Support [23.97212082563385]
  Large language models (LLMs) are already being piloted for clinical use in hospital systems like NYU Langone, Dana-Farber and the NHS. We develop an evaluation framework for determining whether LLM response is a viable and ethical path forward for the automation of mental health treatment.
  arXiv  Detail & Related papers  (2024-05-20T13:42:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.