【LLM 评估】GLUE benchmark:NLU 的多任务 benchmark
论文:GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding ⭐⭐⭐⭐ arXiv:1804.07461, ICLR 2019 Site: https://gluebenchmark.com/ 文章目录 一、论文速读二、GLUE 任务列表2.1 CoLA(Corpus of Linguistic Accep…
2025-09-16