Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision

Open paper
Benchmark Model Rank Results
visual-question-answering-on-mm-vetVOLCANO 13B#83GPT-4 score: 38.0Params: 13B
visual-question-answering-on-mm-vetVOLCANO 7B#132GPT-4 score: 32.0Params: 7B

Rank counts only results with a code link.