Dialogue Planning on ExTES (test)
8.163Average Turn (AT)PPDPP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PPDPPBackbone=Vicuna 13B2026.04 | 8.163 | 55.8 | |
| ICL-AIF2026.04 | 7.65 | 55.5 | |
| LDPP w/o 3rd StageBackbone=Qwen1-1.8B2026.04 | 7.038 | 62.3 | |
| UP-NRPABackbone=GPT-4o mini, level=12026.04 | 4.71 | 99 | |
| LDPP w/o 2nd StageBackbone=Qwen1-1.8B2026.04 | 4.483 | 86.5 | |
| UP-NRPABackbone=GPT-4o mini, level=22026.04 | 4.22 | 100 | |
| LDPPBackbone=Qwen1-1.8B2026.04 | 4.132 | 90.3 | |
| UP-NRPABackbone=Qwen2.5 14B, level=12026.04 | 3.29 | 100 | |
| DialogXpertBackbone=Vicuna 13B2026.04 | 2.97 | 95.34 | |
| DialogXpertBackbone=Qwen1-1.8B2026.04 | 2.73 | 96.51 | |
| UP-NRPABackbone=Qwen2.5 14B, level=22026.04 | 2.69 | 100 | |
| DialogXpertBackbone=Qwen2.5 14B2026.04 | 2.57 | 97.82 |