AI RESEARCH

Fighting Hallucinations with Counterfactuals: Diffusion-Guided Perturbations for LVLM Hallucination Suppression

arXiv CS.CV

ArXi:2603.10470v1 Announce Type: new While large vision-language models (LVLMs) achieve strong performance on multimodal tasks, they frequently generate hallucinations -- unfaithful outputs misaligned with the visual input. To address this issue, we