Response Generation On Argscichat
評価指標
BScore
Message-F1
Mover
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | BScore | Message-F1 | Mover | Paper Title | Repository |
|---|---|---|---|---|---|
| LED(Q,F) | 86.64 | 19.54 | 8.53 | ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers | |
| LED(Q,P,H) | 86.00 | 16.14 | 4.54 | ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers | |
| LED(Q,P) | 85.85 | 14.25 | 2.25 | ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers |
0 of 3 row(s) selected.