Metraipolis › archive › dc_ed28dda060bc
Beetle: A Bilingual Model Suite for Modelling Second-Language Processing — arXiv:2609.22633
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22633
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:49:34.508Z
- SHA-256 of the archived text
0d6f60181531e153af4f57b2b906180da538366a633831114cb196aeea2621c4- Stable URL of this page
https://metraipolis.com/documento/dc_ed28dda060bc
How to cite
Beetle: A Bilingual Model Suite for Modelling Second-Language Processing — arXiv:2609.22633 — arXiv (en), https://arxiv.org/abs/2609.22633 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ed28dda060bc (Metraipolis archive dc_ed28dda060bc, sha256 0d6f60181531e153af4f57b2b906180da538366a633831114cb196aeea2621c4)
BibTeX
@misc{dced28dda060bc,
title = {Beetle: A Bilingual Model Suite for Modelling Second-Language Processing — arXiv:2609.22633},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22633},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ed28dda060bc; sha256 0d6f60181531e153af4f57b2b906180da538366a633831114cb196aeea2621c4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22633. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Bilingual language models (LMs) offer a controlled setting for studying how training conditions shape second-language (L2) behaviour, but prior work typically varies exposure structure, scale, and architecture at once, making it difficult to attribute effects to any single factor. We introduce Beetle, a controlled language model pretraining framework in which tokeniser, target language, training budget, and exposure structure are each independently manipulable, enabling systematic and comparable experimentation of training conditions. Using Beetle, we train and release 285 bilingual and 45 monolingual open-source LMs with rich checkpoints across a range of exposure schedules, data scales and first languages (L1s) to study multilingual pretraining and computational modelling of bilingualism and second language learning. Evaluating models on human bilingual and second language reading-time prediction and grammaticality judgement tasks, we find that staged and temporally structured curricula consistently improve alignment with language learner reading time compared to balanced bilingual training, with the largest gains at smaller data scales and for typologically closer language pairs. The Beetle models are well suited tools to help move computational psycholinguistics beyond its prevailing monolingual, English-centric focus toward models of human bilingual processing, to study cross-lingual learning dynamics, while supporting community-based development of controlled model families. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.22633 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T06:48:44.947Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).