Role-Playing on RPGBench Dialogue Shift (Generalization)
-0.956Turn Composition
RFT
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.12 | -0.956 | -0.583 | |
2025.12 | -0.565 | -0.387 | |
2025.12 | -0.415 | -0.014 | |
2025.12 | -0.362 | -0.018 | |
2025.12 | -0.292 | -0.111 | |
2025.12 | -0.241 | -0.127 | |
2025.12 | -0.218 | -0.059 | |
2025.12 | -0.175 | -0.007 | |
2025.12 | -0.145 | 0.078 | |
2025.12 | -0.105 | 0.116 | |
2025.12 | -0.101 | 0.164 | |
2025.12 | -0.098 | 0.137 | |
2025.12 | -0.081 | 0.132 | |
2025.12 | -0.08 | 0.146 | |
2025.12 | -0.066 | 0.153 | |
2025.12 | -0.057 | 0.149 | |
2025.12 | -0.049 | 0.143 | |
2025.12 | -0.044 | 0.181 |