Conversation Evaluation on Grocery Domain
75.78Human Score (%)GOOD
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GOODinference_type=prob inf2025.08 | 75.78 | 79.44 | |
| GOODinference_type=prompt inf2025.08 | 72.39 | 79.86 | |
| Full Context2025.08 | 68.55 | 76.94 |
| Method | Links | ||
|---|---|---|---|
| GOODinference_type=prob inf2025.08 | 75.78 | 79.44 | |
| GOODinference_type=prompt inf2025.08 | 72.39 | 79.86 | |
| Full Context2025.08 | 68.55 | 76.94 |