AI RESEARCH
LLM Psychosis: A Theoretical and Diagnostic Framework for Reality-Boundary Failures in Large Language Models
arXiv CS.AI
•
ArXi:2604.25934v1 Announce Type: cross The deployment of large language models (LLMs) as interactive agents has exposed a category of behavioral failure that prevailing terminology, principally hallucination, fails to adequately characterize. This paper To operationalize the framework, we propose the LLM Cognitive Integrity Scale (LCIS), a five-axis diagnostic instrument organized around Environmental Reality Interface (ERI), Premise Arbitration Integrity (PAI), Logical Constraint Recognition (LCR), Self-Model Integrity (SMI), and Epistemic Calibration Integrity.