Natural Language Inference on XNLI Ur (test)
0.9643AccuracyBaseline-PS
Evaluation Results
| Method | Links | |
|---|---|---|
| Baseline-PSBackbone=XLMR-large, Input Language=en2026.04 | 0.9643 | |
| Tpl-rand-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=rand-k2024.07 | 0.6518 | |
| Tpl-div-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=div-k2024.07 | 0.6501 | |
| T-div-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=div-k2024.07 | 0.6487 | |
| SRC+GENEvaluation protocol=translate-train2024.07 | 0.6464 | |
| Tpl-top-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=top-k2024.07 | 0.6406 | |
| SRC+GENZero-shot=true2024.07 | 0.6381 | |
| T-top-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=top-k2024.07 | 0.6345 | |
| Tpl-rand-kselection strategy=rand-k, Zero-shot=true2024.07 | 0.6329 | |
| Tpl-div-kselection strategy=div-k, Zero-shot=true2024.07 | 0.6227 | |
| T-top-kselection strategy=top-k, Zero-shot=true2024.07 | 0.6202 | |
| T-rand-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=rand-k2024.07 | 0.6186 | |
| Tpl-top-kselection strategy=top-k, Zero-shot=true2024.07 | 0.6173 | |
| SRCEvaluation protocol=translate-train2024.07 | 0.6134 | |
| SkylineBackbone=XLMR-large, Input Language=ur2026.04 | 0.612 | |
| T-div-kselection strategy=div-k, Zero-shot=true2024.07 | 0.6103 | |
| T-rand-kselection strategy=rand-k, Zero-shot=true2024.07 | 0.5821 | |
| GENEvaluation protocol=translate-train2024.07 | 0.5735 | |
| GENZero-shot=true2024.07 | 0.5659 | |
| SRCZero-shot=true2024.07 | 0.5543 | |
| XITE-reg-regBackbone=XLMR-large, Input Language=en2026.04 | 0.4992 | |
| XITE-reg-ldaBackbone=XLMR-large, Input Language=ur2026.04 | 0.47 | |
| XITE-reg-ldaBackbone=XLMR-large, Input Language=en2026.04 | 0.3695 | |
| XITE-reg-regBackbone=XLMR-large, Input Language=ur2026.04 | 0.344 | |
| SkylineBackbone=XLMR-large, Input Language=en2026.04 | 0.3347 | |
| Baseline-PSBackbone=XLMR-large, Input Language=ur2026.04 | 0.316 |