Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures Paper • 2510.24081 • Published Oct 28, 2025 • 18
AraMix: Recycling, Refiltering, and Deduplicating to Deliver the Largest Arabic Pretraining Corpus Paper • 2512.18834 • Published 23 days ago
SmolKalam: Ensemble Quality-Filtered Translation at Scale for High Quality Arabic Post-Training Data Paper • 2511.18411 • Published Nov 23, 2025
SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs Paper • 2412.08347 • Published Dec 11, 2024 • 4
When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards Paper • 2402.01781 • Published Feb 1, 2024 • 4
Fineweb-Edu-Ar: Machine-translated Corpus to Support Arabic Small Language Models Paper • 2411.06402 • Published Nov 10, 2024 • 2