GLUE基准(General Languag […]
HumanEval是由OpenAI在2021 […]
MMLU(Massive Multitask […]
CIDEr分数(Consensus-base […]
ROUGE分数(Recall-Oriente […]
生成模型评价指标是用于量化评估生成式人工智能 […]
事实核查(Fact-checking)是一种 […]
水印(Watermarking)是一种在数字 […]
内容过滤(Content Filtering […]
毒性(Toxicity)在人工智能领域,特指 […]