AI RESEARCH
Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination
arXiv CS.LG
•
ArXi:2603.19562v1 Announce Type: new Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems, each addressed with modality-specific patches. This study first reveals that they share a common geometric origin: the input and its loss gradient are conjugate observables subject to an irreducible uncertainty bound.