TaskBench
收藏数据链接:
官方服务:
资源简介:
用于评估大型语言模型在任务自动化中能力的基准数据集,通过工具图概念和反向指导方法生成高质量的评估数据集。
A benchmark dataset for evaluating the task automation capabilities of large language models (LLMs), which is generated via the tool graph concept and reverse guidance methodology to produce high-quality evaluation datasets.
创建时间:
2023-12-01



