| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MultiWOZ (test) | EWC+RL | Task Success Rate94 | 68 | 4d ago | |
| MultiWOZ 2.1 (test) | DarwinTOD | BLEU Score22.19 | 49 | 4d ago | |
| MultiWOZ 2.0 (test) | LAVA | Inform Accuracy97.5 | 22 | 4d ago | |
| MultiWOZ 2.2 (test) | FNCTOD-LLAMA2-13B | JGA0.379 | 8 | 4d ago |