HyperAI超神经

Workflow Discovery On Abcd

评估指标

Cross-domain CE
Cross-domain EM
In-domain CE
In-domain EM

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Cross-domain CECross-domain EMIn-domain CEIn-domain EM
workflow-discovery-from-dialogues-in-the-low72.351.875.855.7