MING-ZCH/TFQ-Bench-Lite download history
MING-ZCH/TFQ-Bench-Lite is a visual question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 21 times (8 in the last 7 days), and 277 times in total. It ranks #361,218 among datasets by monthly downloads.
TFQ-Bench: A Benchmark for Evaluating Image Implication Understanding TFQ-Bench is a rigorous evaluation benchmark designed to assess the capabilities of MLLMs in understanding visual metaphors, sarcasm, and implicit meanings via True-False Questions. It serves as a complement to existing