Dialogue response evaluation on DSTC 12 (test)
0.17EmpathyRegression
Evaluation Results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| RegressionMethod Approach=Trained Regression Model2025.08 | 0.17 | 0.2 | 0.07 | 0.24 | 0.24 | -0.1 | 0.14 | 0.08 | 0.09 | 0.13 | 0.15 | |
| BaselineMethod Approach=DSTC-12 Organizer Baseline2025.08 | 0.06 | -0.11 | -0.1 | 0.1 | 0.07 | 0.23 | 0.39 | -0.02 | 0.23 | 0.38 | 0.17 | |
| LM promptingMethod Approach=Large Language Model Prompting2025.08 | -0.08 | 0.01 | -0.22 | 0.05 | 0.13 | 0.08 | 0.11 | -0.15 | 0.37 | 0.31 | 0.15 | |
| HybridMethod Approach=Combined Prompting and Regression2025.08 | -0.08 | 0.01 | -0.22 | 0.24 | 0.13 | -0.1 | 0.14 | 0.08 | 0.09 | 0.31 | 0.14 | |
| ClassificationMethod Approach=Trained Classification Model2025.08 | -0.17 | 0.13 | -0.02 | 0.22 | 0.12 | -0.28 | 0 | 0.2 | 0.08 | -0.17 | 0.14 |