Stereotyping Evaluation on DialogSum
5.6Stereotype FractionGPT-4o-mini
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4o-miniModel=GPT-4o-m2024.07 | 5.6 | 0.543 | 30.9 | |
| Gemini-Flash-LiteModel=Gem-Fl-Lt2024.07 | 7.2 | 0.504 | 30 | |
| Gemini-FlashModel=Gem-Fl2024.07 | 8.3 | 0.413 | 29 | |
| GPT-4oModel=GPT-4o2024.07 | 8.9 | 0.559 | 29.6 | |
| Gemini-ProModel=Gem-Pro2024.07 | 8.9 | 0.496 | 30.5 |