There are 0 repository under gpt-evaluation topic.
BELLE: Be Everyone's Large Language model Engine(开源中文对话大模型)
Evaluating LLMs with CommonGen-Lite
FactScoreLite is an implementation of the FactScore metric, designed for detailed accuracy assessment in text generation. This package builds upon the framework provided by the original FactScore repository, which is no longer maintained and contains outdated functions.