SOURCE-LINKED INTELLIGENCE

Right Tool, Right Job: Native-Language Evaluation, Tokenizer Sensitivity, and Methodological Findings from a French-Only BabyLM

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

We submit MéTRON-FR, a 125M GPT-2 pretrained on 92.47M words of French, to the BabyLM 2026 Strict track. It scores 85.97 +/- 0.17% on QFrBLiMP (a native Quebec-French benchmark of grammatical minimal pairs) and 62.80% on the BabyLM-weighted leaderboard. A cross-lingual GLUE (General Language Understanding Evaluation) protocol that combines French task-data translation with rank-16 LoRA (Low-Rank Adaptation) produces a sharp task-type gradient: relational tasks gain measurably, while world-knowledge tasks regress. Bilingual Lexicon Induction aligns the French embeddings to GPT-2 at p@1 = 68.84

Read original source ↗ Open in workspace

recordType

paper

region

Global