HyperAI超神经

Human Judgment Correlation On Flickr8K Expert

评估指标

Kendall's Tau-c

评测结果

各个模型在此基准测试上的表现结果

比较表格
模型名称Kendall's Tau-c
clipscore-a-reference-free-evaluation-metric51.2
factual-a-benchmark-for-faithful-and54.2
mutual-information-divergence-a-unified54.9
clipscore-a-reference-free-evaluation-metric53.0