LLMEval2
收藏OpenXLab2026-04-18 收录
官方服务：
资源简介：
LLMEval² for LLM evaluators, comprising 15 tasks, 8 abilities, and 2,553 samples. Experimental results demonstrate that a wider network (involving many reviewers) with 2 layers (one round of discussion) performs the best, improving kappa correlation coefficient from 0.28 to 0.34.
提供机构：
OpenDataLab创建时间：
2024-04-30
