对于自动评分器而言,简化设计更有利于实现经济高效的开放式任务大型语言模型(LLM)评估.pdf

对于自动评分器而言,简化设计更有利于实现经济高效的开放式任务大型语言模型(LLM)评估.pdf

ResearchReport

SUNISHCHALDEV,PATRICIAPASKOV,ANDREWSLOAN,KEVINWEI,

PEDRONASCIMENTODELIMA,SWAPTIKCHOWDHURY,JASONJOHNSON,

WILLIAMMARCELLINO

SimplerIsBetter

forAutograders

TowardCost-EffectiveLLMEvaluationsforOp

文档评论(0)

1亿VIP精品文档

相关文档