AI Psychosis: Does Conversational AI Amplify Delusion-Related Language?

arXiv:2603.19574 · cs.HC, cs.AI, cs.CL, cs.CY, cs.SI · Submitted 2026-03-20 · Read on arXiv

cs.HC, cs.AI, cs.CL, cs.CY, cs.SI

Submitted: 2026-03-20

Updated: 2026-09-13

Comments: EMNLP 2026

Journal ref: Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), Main Conference

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Embeddings — 6× in this paper · explained in 2 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Hallucination — 4× in this paper · explained in 3 episodes
• Commentary — 3× in this paper · explained in 2 episodes
• ACM Transactions on Computer-Human Interaction — 2× in this paper
• Accountability — 2× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Sycophancy — 2× in this paper · explained in 4 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Causal Inference — 1× in this paper · explained in 4 episodes
• Conference on Human Factors in Computing Systems — 1× in this paper
• Epistemic Uncertainty — 1× in this paper · explained in 9 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Personalization — 1× in this paper · explained in 2 episodes

Sources

• Technological folie \`a deux: Feedback Loops Between AI Chatbots and Mental Illness
• The Psychogenic Machine: Simulating AI Psychosis, Delusion Reinforcement and Harm Enablement in Large Language Models
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• RubRIX: Rubric-Driven Risk Mitigation in Caregiver-AI Interactions
• BERTopic: Neural topic modeling with a class-based TF-IDF procedure
• InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
• Eliciting Behaviors in Multi-Turn Conversations
• PAIR-SAFE: A Paired-Agent Approach for Runtime Auditing and Refining AI-Mediated Mental Health Support
• Interpretable Depression Detection from Social Media Text Using LLM-Derived Embeddings
• Interpersonal Theory of Suicide as a Lens to Examine Suicidal Ideation in Online Spaces
• AI Chatbots for Mental Health: Values and Harms from Lived Experiences of Depression
• Can LLM "Self-report"?: Evaluating the Validity of Self-report Scales in Measuring Personality Design in LLM-based Chatbots

Related papers

• EduGage: A Multimodal Dataset and Benchmark for Sensor-Based Momentary Assessment of Engagement in Self-Guided Video Learning
• EvoDesign: Agentic Editable Diagram Creation via Design Expertise Evolution
• HAGI++: Head-Assisted Gaze Imputation and Generation
• Linking Behaviour and Perception to Evaluate Meaningful Human Control over Partially Automated Driving
• Review of Explainable Decision Support and Adaptive Human-Machine Interfaces for Automation Transparency in Maritime Autonomous Surface Ships
• Towards Cognitive Process-Aware Proactive Writing Support