Natural Language Inference on XNLI Sw (test)
65.34AccuracyTpl-div-k
Evaluation Results
| Method | Links | |
|---|---|---|
| Tpl-div-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=div-k2024.07 | 65.34 | |
| SRC+GENEvaluation protocol=translate-train2024.07 | 64.3 | |
| Tpl-rand-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=rand-k2024.07 | 64.11 | |
| T-div-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=div-k2024.07 | 64.1 | |
| Tpl-top-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=top-k2024.07 | 63.78 | |
| SRC+GENZero-shot=true2024.07 | 63.64 | |
| T-top-kselection strategy=top-k, Zero-shot=true2024.07 | 62.94 | |
| T-top-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=top-k2024.07 | 62.9 | |
| Tpl-rand-kselection strategy=rand-k, Zero-shot=true2024.07 | 62.49 | |
| Tpl-div-kselection strategy=div-k, Zero-shot=true2024.07 | 61.86 | |
| T-div-kselection strategy=div-k, Zero-shot=true2024.07 | 61.51 | |
| Tpl-top-kselection strategy=top-k, Zero-shot=true2024.07 | 61.18 | |
| T-rand-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=rand-k2024.07 | 60.97 | |
| T-rand-kselection strategy=rand-k, Zero-shot=true2024.07 | 59.49 | |
| SRCEvaluation protocol=translate-train2024.07 | 58.54 | |
| GENEvaluation protocol=translate-train2024.07 | 56.23 | |
| GENZero-shot=true2024.07 | 56.17 | |
| SRCZero-shot=true2024.07 | 55.45 |