AI RESEARCH

On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods

arXiv CS.LG

ArXi:2605.13146v1 Announce Type: cross Artificial intelligence (AI) has transformed imaging inverse problems, from medical diagnostics to Earth observation. Yet deep neural networks can produce hallucinations, realistic-looking but incorrect details, undermining their reliability, especially when ground truth data is unavailable. We develop a theoretical framework showing that such hallucinations are not merely artifacts of particular models, but can arise from the ill-posed nature of the inverse problem itself.