Question Answering On Multitq
평가 지표
Hits@1
Hits@10
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Hits@1 | Hits@10 |
|---|---|---|
| question-answering-over-temporal-knowledge | 27.9 | 63.5 |
| muti-view-mouse-social-behaviour-recognition | 29.3 | 44.1 |
| distilbert-a-distilled-version-of-bert | 8.3 | 48.4 |
| improving-multi-hop-question-answering-over | 20.6 | 60.8 |
| bert-pre-training-of-deep-bidirectional | 8.3 | 48.2 |
| 모델 6 | 10.2 | - |
| self-improvement-programming-for-temporal | 79.7 | 91 |
| llama-2-open-foundation-and-fine-tuned-chat | 18.5 | - |
| temporal-knowledge-question-answering-via | 38 | - |
| albert-a-lite-bert-for-self-supervised | 10.8 | 45.9 |
| 모델 11 | 72.8 | - |