HyperAI超神经

Bias Detection On Stereoset 1

评估指标

ICAT Score
LMS
SS

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ICAT ScoreLMSSS
galactica-a-large-language-model-for-science-16074.859.9
stereoset-measuring-stereotypical-bias-in71.73--
stereoset-measuring-stereotypical-bias-in69.89--
stereoset-measuring-stereotypical-bias-in70.54--
galactica-a-large-language-model-for-science-165.67556.2
stereoset-measuring-stereotypical-bias-in72.03--
stereoset-measuring-stereotypical-bias-in62.10--
stereoset-measuring-stereotypical-bias-in71.21--
stereoset-measuring-stereotypical-bias-in67.50--
galactica-a-large-language-model-for-science-160.877.660.8
stereoset-measuring-stereotypical-bias-in72.97--