MM-Hallu/R-Bench download history

MM-Hallu/R-Bench is a visual question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 141 times (36 in the last 7 days), and 2,542 times in total. It ranks #88,351 among datasets by monthly downloads.

R-Bench Benchmark for evaluating relationship hallucinations in LVLMs. Features image-level and instance-level questions focusing on inter-object relationships. Fields Field Description image Input image question_id Question identifier question Question about ima

Open MM-Hallu/R-Bench on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.