The Dynamics of Delusion: Modeling Bidirectional False Belief Amplification in Human-Chatbot Dialogue
cs.CL, cs.HC
Submitted: 2026-04-28
Updated: 2026-10-12
Code: https://github.com/sampaech/spiral-bench
Sources
- Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning
- Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians
- Technological folie \`a deux: Feedback Loops Between AI Chatbots and Mental Illness
- LLM Spirals of Delusion: A Benchmarking Audit Study of AI Chatbot Interfaces
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Towards Understanding Sycophancy in Language Models
- Confabulation: The Surprising Value of Large Language Model Hallucinations
- Clio: Privacy-Preserving Insights into Real-World AI Use
- The Psychogenic Machine: Simulating AI Psychosis, Delusion Reinforcement and Harm Enablement in Large Language Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering