UCCIX: Irish-eXcellence Large Language Model (2024 · 14 citations)
Irish is a UNESCO "definitely endangered" language with only a few hundred million tokens of available text, far below what scaling laws suggest for training an LLM.
Qomhrá: A Bilingual Irish and English Large Language Model (2026 · 2 citations)
Irish has very little language technology support among official EU languages, and permissively licensed labelled data for instruction tuning and alignment is especially scarce.
Disentangling Continued Pre-Training: Attention-Driven Routing and Semantic Hub Preservation in Language Adaptation (2026 · 1 citation)
The paper examines what happens inside an LLM during Continued Pre-Training (CPT), the process that teaches it a second language. The authors trace the full training trajectory instead of only the final checkpoint. They use English as the base language and three targets: Irish, Basque, and Chinese. The models are:
LaCoMSA: Language-Consistency Multilingual Self-Alignment with Latent Representation Rewarding (2026)
Multilingual LLMs tend to answer worse in lower-resource languages than in English. They also often switch into English even when prompted in another language. Earlier preference-optimization fixes such as MAPO, LIDR and ICR depend on outside supervision, such as translation systems or English-trained reward models.

Co-authors here

2 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 15 times (of the 149,439 papers whose bibliographies we read); 3 citing papers with a page here →.

Updated 1 November 2026