Question Answering On Timequestions
Métriques
P@1
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | P@1 |
|---|---|
| conversational-question-answering-on | 42.3 |
| complex-temporal-question-answering-on | 56.5 |
| openai-s-gpt4-as-coding-assistant | 30.6 |
| Modèle 4 | 52.9 |
| Modèle 5 | 53.6 |
| uniqorn-unified-question-answering-over-rdf | 33.1 |
| Modèle 7 | 78.1 |
| rag-based-question-answering-over | 75.4 |
| explainable-conversational-question-answering | 52.5 |
| time-aware-multiway-adaptive-fusion-network | 43.6 |
| faithful-temporal-question-answering-over | 53.5 |
| semantic-framework-based-query-generation-for | 53.9 |
| Modèle 13 | 46.5 |
| twirgcn-temporally-weighted-graph-convolution | 60.5 |
| training-language-models-to-follow | 22.4 |
| graphnet-graph-neural-networks-for-neutrino | 45.2 |
| pullnet-open-domain-question-answering-with | 10.5 |
| tempoqr-temporal-question-reasoning-over | 43.8 |
| question-answering-over-temporal-knowledge | 39.5 |
| llama-open-and-efficient-foundation-language-1 | 17.8 |
| Modèle 21 | 42.4 |