| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| SOTOPIA Interaction with GPT-4o | LLaMA-8B+BC+ALPO | Goal Score8.21 | 28 | 4d ago | |
| SOTOPIA Self-Chat | Llama-8B+BC+SDPO | GOAL8.56 | 28 | 4d ago | |
| SOTOPIA Overall (AVG) | Llama-8B+BC+SDPO | AVG Score5.63 | 11 | 4d ago | |
| SOTOPIA Interaction with GPT-4o-mini | GOAL Score7.53 | 11 | 4d ago |