List your company
ResearchFormerly WizWand

Natural Language Inference on XNLI Sw (dev)

65.68AccuracyTpl-div-k
55.633658.241860.8563.4582Jul 15, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Tpl-div-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=div-k2024.0765.68
T-div-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=div-k2024.0764.44
Tpl-top-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=top-k2024.0764.38
Tpl-div-kselection strategy=div-k, Zero-shot=true2024.0763.88
Tpl-rand-kEvaluation protocol=translate-train, Supervision type=hard prompt labels, Data selection strategy=rand-k2024.0763.88
T-top-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=top-k2024.0763.82
T-top-kselection strategy=top-k, Zero-shot=true2024.0763.74
SRC+GENEvaluation protocol=translate-train2024.0763.52
SRC+GENZero-shot=true2024.0763.34
Tpl-rand-kselection strategy=rand-k, Zero-shot=true2024.0763.24
T-div-kselection strategy=div-k, Zero-shot=true2024.0762.69
Tpl-top-kselection strategy=top-k, Zero-shot=true2024.0762.11
T-rand-kEvaluation protocol=translate-train, Supervision type=teacher soft pseudolabels, Data selection strategy=rand-k2024.0762.11
T-rand-kselection strategy=rand-k, Zero-shot=true2024.0761.67
SRCEvaluation protocol=translate-train2024.0759.16
SRCZero-shot=true2024.0757.63
GENEvaluation protocol=translate-train2024.0756.71
GENZero-shot=true2024.0756.02