Dialogue-level evaluation
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Dialogue Generation | Dialogue-level evaluation Ethical and Affective Alignment | Respectful Tone8.1739 | 9 | |
| Dialogue-level Guidance Quality Evaluation | Dialogue-level evaluation (N=54) | State Tracking3.3 | 6 |
Showing 2 of 2 rows