List your company

Natural Language Inference on XNLI Ur (test)

0.9643AccuracyBaseline-PS
0.2900680.4651090.640150.815191Jul 15, 2024Oct 31, 2024Feb 16, 2025Jun 5, 2025Sep 21, 2025Jan 7, 2026Apr 26, 2026

Evaluation results

MethodLinks
Baseline-PSBackbone=XLMR-large, Input Language=en2026.040.9643
Tpl-rand-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=rand-k2024.070.6518
Tpl-div-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=div-k2024.070.6501
T-div-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=div-k2024.070.6487
SRC+GENEvaluation protocol=translate-train2024.070.6464
Tpl-top-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=top-k2024.070.6406
SRC+GENZero-shot=true2024.070.6381
T-top-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=top-k2024.070.6345
Tpl-rand-kselection strategy=rand-k, Zero-shot=true2024.070.6329
Tpl-div-kselection strategy=div-k, Zero-shot=true2024.070.6227
T-top-kselection strategy=top-k, Zero-shot=true2024.070.6202
T-rand-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=rand-k2024.070.6186
Tpl-top-kselection strategy=top-k, Zero-shot=true2024.070.6173
SRCEvaluation protocol=translate-train2024.070.6134
SkylineBackbone=XLMR-large, Input Language=ur2026.040.612
T-div-kselection strategy=div-k, Zero-shot=true2024.070.6103
T-rand-kselection strategy=rand-k, Zero-shot=true2024.070.5821
GENEvaluation protocol=translate-train2024.070.5735
GENZero-shot=true2024.070.5659
SRCZero-shot=true2024.070.5543
XITE-reg-regBackbone=XLMR-large, Input Language=en2026.040.4992
XITE-reg-ldaBackbone=XLMR-large, Input Language=ur2026.040.47
XITE-reg-ldaBackbone=XLMR-large, Input Language=en2026.040.3695
XITE-reg-regBackbone=XLMR-large, Input Language=ur2026.040.344
SkylineBackbone=XLMR-large, Input Language=en2026.040.3347
Baseline-PSBackbone=XLMR-large, Input Language=ur2026.040.316