Shayne Longpre @shaynelongpre.bsky.social · 28/10/2025Q1: Can we build a scaling law that generalizes to unseen model sizes (N), data amounts (D), AND language mixtures (M)? 🌟Answer: Yes! ATLAS outperforms prior work with R²(N)=0.88 vs 0.68, and R²(M)=0.82 vs 0.69 for mixture generalization. 2/ 100
Shayne Longpre @shaynelongpre.bsky.social · 28/10/2025ATLAS models cross-lingual transfer explicitly: separating (1) target language data, (2) beneficial transfer languages, and (3) other languages. Without modeling transfer, existing laws fail on multilingual settings. 3/ 100
Shayne Longpre @shaynelongpre.bsky.social · 28/10/2025Q2: Which languages actually help each other during training? And how much? 🌟Answer: We measure this empirically. We built a 38×38 transfer matrix, or 1,444 language pairs—the largest such resource to date. We highlight the top 5 most beneficial source languages for each target language. 4/ 100
