| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| PersonaChat (Human Evaluation) | Persona Generator | Fluency3.58 | 16 | 1mo ago | |
| ConvAI2 (Human Evaluation) | Readability80 | 8 | 1mo ago | ||
| Baidu PersonaChat | CLV | BLEU-124.77 | 7 | 1mo ago | |
| ConvAI2 | CLV | BLEU-111.85 | 7 | 1mo ago | |
| Session-level evaluation dataset 1.0 (test) | Muse | Personalization Consistency83.78 | 6 | 2d ago | |
| DailyDialog | Persona Generator | Fluency3.5 | 3 | 1mo ago |
