Knowledge Base Question Answering On
評価指標
Accuracy
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
比較表
| モデル名 | Accuracy |
|---|---|
| improving-multi-hop-knowledge-base-question | 53.9 |
| case-based-reasoning-for-natural-language | 44.1 |
| chatkbqa-a-generate-then-retrieve-framework | 76.8 |
| case-based-reasoning-for-natural-language | 45.9 |
| paths-over-graph-knowledge-graph-enpowered | - |
| case-based-reasoning-for-natural-language | 70.4 |