Social Dialogue on SOTOPIA Self-Chat
8.56GOAL
Llama-8B+BC+SDPO
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.01 | 8.56 | 3.69 | |
2026.02 | 8.56 | 3.69 | |
2025.01 | 8.48 | 3.49 | |
2026.02 | 8.41 | 3.56 | |
2025.01 | 8.34 | 3.26 | |
2025.01 | 8.3 | 3.27 | |
2025.01 | 8.29 | 3.39 | |
2026.02 | 8.29 | 3.39 | |
2025.01 | 8.28 | 3.37 | |
2026.02 | 8.28 | 3.37 | |
2025.01 | 8.18 | 2.96 | |
2026.02 | 8.18 | 2.96 | |
2025.01 | 8.13 | 3.13 | |
2025.01 | 7.95 | 3.28 | |
2026.02 | 7.95 | 3.28 | |
2025.01 | 7.9 | 2.67 | |
2026.02 | 7.9 | 2.67 | |
2025.01 | 7.89 | 2.98 | |
2025.01 | 7.81 | 3.05 | |
2026.02 | 7.81 | 3.05 | |
2025.01 | 7.76 | 3.05 | |
2026.02 | 7.76 | 3.05 | |
2025.01 | 7.24 | 1.94 | |
2026.02 | 7.24 | 1.94 | |
2025.01 | 6.98 | 2.11 | |
2026.02 | 6.98 | 2.11 | |
2025.01 | 6.38 | 1.36 | |
2026.02 | 6.38 | 1.36 |