ChatGPT中文性能测评与风险应对*

张华平,李林翰,李春锦

ChatGPT Performance Evaluation on Chinese Language and Risk Measures

Zhang Huaping,Li Linhan,Li Chunjin

表3 中文文本摘要任务的性能测试实验

Table 3 Evaluation Experiments on Text Summary Tasks

数据集 评估指标 WeLM PanGu-α ChatGPT ERNIE 3.0 Titan LCSTS ROUGE-1 23.74 — 31.30 — TTNews ROUGE-1 35.06 — 42.92 —