Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance

ArXi:2602.01047v3 Announce Type: replace-cross Large Vision-Language Models (LVLMs) can reason from image-text inputs and perform well in various multimodal tasks. Despite this success, they are affected by language priors and often produce hallucinations. Hallucinations denote generated content that is grammatically and syntactically coherent, yet bears no match or direct relevance to visual input. To address this problem, we propose Residual Decoding (ResDec). It is a novel