Question Answering On Cronquestions
Metriken
Hits@1
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Hits@1 |
|---|---|
| time-aware-multiway-adaptive-fusion-network | 78.4 |
| Modell 2 | 15.1 |
| Modell 3 | 28.8 |
| tempoqr-temporal-question-reasoning-over | 24.3 |
| Modell 5 | 28.8 |
| Modell 6 | 75.4 |
| tempoqr-temporal-question-reasoning-over | 74.5 |
| Modell 8 | 81.1 |
| Modell 9 | 7.1 |
| question-calibration-and-multi-hop-modeling | 97.1 |
| Modell 11 | 22.6 |
| self-improvement-programming-for-temporal | 93.7 |
| improving-time-sensitivity-for-question | 83.1 |
| Modell 14 | 92 |
| two-stage-generative-question-answering-on | 97.8 |
| Modell 16 | 96.9 |
| Modell 17 | 7 |
| Modell 18 | 80.6 |
| tempoqr-temporal-question-reasoning-over | 91.8 |
| Modell 20 | 92 |
| Modell 21 | 96.9 |
| temporal-knowledge-graph-question-answering | 96.6 |
| Modell 23 | 22.5 |
| question-answering-over-temporal-knowledge | 64.7 |
| tempoqr-temporal-question-reasoning-over | 79.9 |
| Modell 26 | 27.8 |
| Modell 27 | 28.8 |
| Modell 28 | 90.9 |
| Modell 29 | 25.2 |