List your company
ResearchFormerly WizWand

Natural Language Inference on XNLI Hi (test)

71.65AccuracyT-div-k
60.220463.187766.15569.1223Jul 15, 2024
Updated 8mo ago

Evaluation results

MethodLinks
T-div-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=div-k2024.0771.65
T-top-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=top-k2024.0771.41
Tpl-rand-kselection strategy=rand-k, Zero-shot=true2024.0771.19
T-rand-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=rand-k2024.0771.12
Tpl-rand-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=rand-k2024.0771.12
Tpl-div-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=div-k2024.0770.88
Tpl-top-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=top-k2024.0770.39
SRC+GENZero-shot=true2024.0770.2
Tpl-div-kselection strategy=div-k, Zero-shot=true2024.0769.89
Tpl-top-kselection strategy=top-k, Zero-shot=true2024.0769.86
T-top-kselection strategy=top-k, Zero-shot=true2024.0769.81
T-div-kselection strategy=div-k, Zero-shot=true2024.0769.65
SRC+GENEvaluation protocol=translate-train2024.0769.29
SRCEvaluation protocol=translate-train2024.0767.72
T-rand-kselection strategy=rand-k, Zero-shot=true2024.0767.68
SRCZero-shot=true2024.0764.61
GENZero-shot=true2024.0762.06
GENEvaluation protocol=translate-train2024.0760.66