Proactive Dialogue Generation on DuRecDial OOD 2.0 (test)
1.3PerplexityQwen
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| QwenModel Size=32B, Evaluation Protocol=Prompt-based2026.05 | 1.3 | 25.92 | 0.186 | 0.093 | 0.02 | 0.114 | 33.97 | 5.3 | |
| QwenModel Size=14B, Evaluation Protocol=Prompt-based2026.05 | 1.34 | 26.38 | 0.192 | 0.096 | 0.023 | 0.128 | 39.08 | 6.23 | |
| LLaMAModel Size=8B, Evaluation Protocol=Prompt-based2026.05 | 1.53 | 26.03 | 0.196 | 0.101 | 0.021 | 0.116 | 32.93 | 5.61 | |
| QwenModel Size=3B, Evaluation Protocol=Fine-tuning2026.05 | 4.17 | 39.84 | 0.357 | 0.255 | 0.031 | 0.13 | 58.66 | 28.35 | |
| LLaMAModel Size=3B, Evaluation Protocol=Fine-tuning2026.05 | 4.32 | 40.94 | 0.362 | 0.262 | 0.031 | 0.123 | 59.57 | 36.14 | |
| LLaMAModel Size=1B, Evaluation Protocol=Fine-tuning2026.05 | 4.83 | 39.34 | 0.358 | 0.256 | 0.031 | 0.129 | 55.19 | 41.12 | |
| Our0.3B (soft)Inference Mode=Soft2026.05 | 7.13 | 39.84 | 0.365 | 0.253 | 0.021 | 0.079 | 49.27 | 23.68 | |
| Our0.3B (hard)Inference Mode=Hard2026.05 | 7.27 | 39.61 | 0.363 | 0.252 | 0.022 | 0.082 | 49.44 | 23.68 |