List your company

Multilingual Commonsense Reasoning on XStoryCloze

70.4Accuracy (en)Pythia-6.9B
43.46450.45757.4564.443Jun 4, 2025

Evaluation results

MethodLinks
Pythia-6.9BInitialization=Vanilla, Zero-shot=true2025.0670.453.950.353.8—
TokAlign + LATBackbone=Pythia-6.9B, Initialization=TokAlign, Language Adaptation Tuning (+LAT)=true, Zero-shot=true2025.0670.254.449.353.9—
TokAlignBackbone=Pythia-6.9B, Initialization=TokAlign, Zero-shot=true2025.0666.848.647.750—
Pythia-1BInitialization=Vanilla, Zero-shot=true2025.0664.348.64852.9—
TokAlign + LATBackbone=Pythia-1B, Initialization=TokAlign, Language Adaptation Tuning (+LAT)=true, Zero-shot=true2025.066451.147.853.5—
TokAlignBackbone=Pythia-1B, Initialization=TokAlign, Zero-shot=true2025.066147.647.151—
Focus + LATBackbone=Pythia-6.9B, Initialization=Focus, Language Adaptation Tuning (+LAT)=true, Zero-shot=true2025.066148.747.753.7—
ZeTT + LATBackbone=Pythia-1B, Initialization=ZeTT, Language Adaptation Tuning (+LAT)=true, Zero-shot=true2025.0660.349.347.252.1—
Focus + LATBackbone=Pythia-1B, Initialization=Focus, Language Adaptation Tuning (+LAT)=true, Zero-shot=true2025.0655.848.847.650.4—
ZeTTBackbone=Pythia-1B, Initialization=ZeTT, Zero-shot=true2025.0653.246.946.948.1—
FocusBackbone=Pythia-1B, Initialization=Focus, Zero-shot=true2025.0645.947.848.846.5—
FocusBackbone=Pythia-6.9B, Initialization=Focus, Zero-shot=true2025.0644.547.147.847.1—
EuroLMscenario=zero-shot2025.12————56.5
Gamayunscenario=zero-shot2025.12————60.5
Gemma3scenario=zero-shot2025.12————56.3
Llama3.2scenario=zero-shot2025.12————50.5
Qwen2.5scenario=zero-shot2025.12————55.2
Qwen3scenario=zero-shot, thinking_mode=no-thinking2025.12————52.4