Personalized Response Generation on Assistant and Summary personalization tasks (test)
83.91Win Ratevol-mo
Evaluation Results
| Method | Links | |
|---|---|---|
| vol-moOpponent=vol-un2024.11 | 83.91 | |
| vol-moOpponent=rnd-un2024.11 | 82.35 | |
| vol-moOpponent=rnd-mo2024.11 | 75.7 | |
| rnd-moOpponent=vol-un2024.11 | 60.62 | |
| rnd-moOpponent=rnd-un2024.11 | 58.99 | |
| rnd-unOpponent=vol-un2024.11 | 52.44 | |
| vol-unOpponent=rnd-un2024.11 | 47.56 | |
| rnd-unOpponent=rnd-mo2024.11 | 41.01 | |
| vol-unOpponent=rnd-mo2024.11 | 39.38 | |
| rnd-moOpponent=vol-mo2024.11 | 24.3 | |
| rnd-unOpponent=vol-mo2024.11 | 17.65 | |
| vol-unOpponent=vol-mo2024.11 | 16.09 |