UltraEval is an open-source framework for evaluating the capabilities of foundation models, providing a suite of lightweight, easy-to-use evaluation systems that support the performance assessment of mainstream LLMs. github.com/OpenBMB/UltraEval
[IR] MS MARCO Web Search: a Large-scale Information-rich Web Dataset with Millions of Real Click Labels 网页链接 提出了MS MARCO Web Search大规模真实网页数据集和检索基准,推动信息检索研究进入万亿规模并接近真实应用。