Explanation-rating coherence evaluation on Baby
83.34GPT ScoreCurr-RLCER
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Curr-RLCER2026.04 | 83.34 | 91.91 | 86.17 | |
| PETER2026.04 | 70.13 | 81.19 | 69.15 | |
| CER2026.04 | 69.88 | 79.96 | 75.61 | |
| NRT2026.04 | 68.24 | 80.49 | 70.28 |
| Method | Links | |||
|---|---|---|---|---|
| Curr-RLCER2026.04 | 83.34 | 91.91 | 86.17 | |
| PETER2026.04 | 70.13 | 81.19 | 69.15 | |
| CER2026.04 | 69.88 | 79.96 | 75.61 | |
| NRT2026.04 | 68.24 | 80.49 | 70.28 |