R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs

ArXi:2604.20696v1 Announce Type: new Large vision-language models (LVLMs) have nstrated impressive performance in various multimodal understanding and reasoning tasks. However, they still struggle with object hallucinations, i.e., the claim of nonexistent objects in the visual input. To address this challenge, we propose Region-aware Chain-of-Verification (R-CoV), a visual chain-of-verification method to alleviate object hallucinations in LVLMs in a post-hoc manner.