符号推理(Symbolic Reasonin […]
常识推理(Common Sense Reas […]
推理能力(Reasoning Ability […]
指令遵循(Instruction Follo […]
Winograd Schema Challe […]
SuperGLUE基准(SuperGLUE […]
GLUE基准(General Languag […]
HumanEval是由OpenAI在2021 […]
GSM8K(Grade School Mat […]
MMLU(Massive Multitask […]