Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yeung, Joshua Au, Dalmasso, Jacopo, Foschini, Luca, Dobson, Richard JB, Kraljevic, Zeljko
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Large Language Models for Medical Forecasting -- Foresight 2
par: Kraljevic, Zeljko, et autres
Publié: (2024)

Hallucinating with AI: AI Psychosis as Distributed Delusions
par: Osler, Lucy
Publié: (2025)

AI Psychosis: Does Conversational AI Amplify Delusion-Related Language?
par: Shimgekar, Soorya Ram, et autres
Publié: (2026)

Delusions of Large Language Models
par: Xu, Hongshen, et autres
Publié: (2025)

Unlocking Electronic Health Records: A Hybrid Graph RAG Approach to Safe Clinical AI for Patient QA
par: Thio, Samuel, et autres
Publié: (2025)

FastOMOP: A Foundational Architecture for Reliable Agentic Real-World Evidence Generation on OMOP CDM data
par: Moeller-Grell, Niko, et autres
Publié: (2026)

Grounding Large Language Models in Clinical Evidence: A Retrieval-Augmented Generation System for Querying UK NICE Clinical Guidelines
par: Lewis, Matthew, et autres
Publié: (2025)

Self-HarmLLM: Can Large Language Model Harm Itself?
par: Kim, Heehwan, et autres
Publié: (2025)

Purposefully Induced Psychosis (PIP): Embracing Hallucination as Imagination in Large Language Models
par: Pilcher, Kris, et autres
Publié: (2025)

A Novel Zero-Touch, Zero-Trust, AI/ML Enablement Framework for IoT Network Security
par: Shakya, Sushil, et autres
Publié: (2025)

AI Meets the Classroom: When Do Large Language Models Harm Learning?
par: Lehmann, Matthias, et autres
Publié: (2024)

Why Do Large Language Models Generate Harmful Content?
par: Ganguli, Rajesh, et autres
Publié: (2026)

Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
par: Huang, Tiansheng, et autres
Publié: (2024)

LLM Psychosis: A Theoretical and Diagnostic Framework for Reality-Boundary Failures in Large Language Models
par: Raj, Ashutosh
Publié: (2026)

LLM Spirals of Delusion: A Benchmarking Audit Study of AI Chatbot Interfaces
par: Kirgis, Peter, et autres
Publié: (2026)

Manipulation and the AI Act: Large Language Model Chatbots and the Danger of Mirrors
par: Krook, Joshua
Publié: (2025)

The Depth Delusion: Why Transformers Should Be Wider, Not Deeper
par: Fahim, Md Muhtasim Munif, et autres
Publié: (2026)

Prefix Probing: Lightweight Harmful Content Detection for Large Language Models
par: Yang, Jirui, et autres
Publié: (2025)

Developing and Evaluating an AI-Assisted Prediction Model for Unplanned Intensive Care Admissions following Elective Neurosurgery using Natural Language Processing within an Electronic Healthcare Record System
par: Ive, Julia, et autres
Publié: (2025)

Harm in AI-Driven Societies: An Audit of Toxicity Adoption on Chirper.ai
par: Coppolillo, Erica, et autres
Publié: (2026)

AI for Distributed Systems Design: Scalable Cloud Optimization Through Repeated LLMs Sampling And Simulators
par: Tagliabue, Jacopo
Publié: (2025)

Knowledge as Enablement
Publié: (2023)

Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink
par: Liu, Guozhi, et autres
Publié: (2026)

The DCR Delusion: Measuring the Privacy Risk of Synthetic Data
par: Yao, Zexi, et autres
Publié: (2025)

Evaluating Language Models for Harmful Manipulation
par: Akbulut, Canfer, et autres
Publié: (2026)

Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models
par: Yang, Fan
Publié: (2025)

Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content
par: Bianchi, Federico, et autres
Publié: (2024)

RealHarm: A Collection of Real-World Language Model Application Failures
par: Jeune, Pierre Le, et autres
Publié: (2025)

OSPC: Detecting Harmful Memes with Large Language Model as a Catalyst
par: Cao, Jingtao, et autres
Publié: (2024)

AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness
par: Chen, Zixin, et autres
Publié: (2025)

Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments
par: Muminovic, Amel
Publié: (2025)

Code Red! On the Harmfulness of Applying Off-the-shelf Large Language Models to Programming Tasks
par: Al-Kaswan, Ali, et autres
Publié: (2025)

VaccineRAG: Boosting Multimodal Large Language Models' Immunity to Harmful RAG Samples
par: Sun, Qixin, et autres
Publié: (2025)

Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
par: Huang, Tiansheng, et autres
Publié: (2024)

Helpful or Harmful? Exploring the Efficacy of Large Language Models for Online Grooming Prevention
par: Prosser, Ellie, et autres
Publié: (2024)

Interactive Navigation in Environments with Traversable Obstacles Using Large Language and Vision-Language Models
par: Zhang, Zhen, et autres
Publié: (2023)

Harmful Traits of AI Companions
par: Knox, W. Bradley, et autres
Publié: (2025)

Model-Based Reinforcement Learning under Random Observation Delays
par: Karamzade, Armin, et autres
Publié: (2025)

Complacent, Not Sycophantic: Reframing Large Language Models and Designing AI Literacy for Complacent Machines
par: Germani, Federico, et autres
Publié: (2026)

Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machine
par: Alsadat, Shayan Meshkat, et autres
Publié: (2024)