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7
中文闭卷问答的性能测试实验
Table 7
Evaluation Experiments on Chinese Closed Book Questions and Answers
数据集
评价指标
WeLM
PanGu-α
ChatGPT
ERNIE 3.0 Titan
WebQA
EM/F1
-/50.90
5.13/14.47
0.10/ 0.34
37.97/52.57
CKBQA
Acc/%
—
14.21
16.47
24.12