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1 中文情感分析任务的性能测试实验结果

Table 1 Evaluation Experiments on Sentiment Analysis Tasks

数据集 评估指标 WeLM PanGu-α ChatGPT ERNIE 3.0 Titan ChnSentiCorp Acc/% 81.58 — 87.50 — EPRSTMT Acc/% — — 85.90 88.75