3 papers
cs.CL2026
Toward LLMs Beyond English-Centric Development
Sho Takase, Ukyo Honda
Through an analysis of sequences generated by open-weight large language models (LLMs), we demonstrate that LLMs are heavily biased toward English. While continual pre-training is…
cs.CL2026
Does Self-Consistency Improve the Recall of Encyclopedic Knowledge?
Sho Hoshino, Ukyo Honda, Peinan Zhang
While self-consistency is known to improve performance on symbolic reasoning, its effect on the recall of encyclopedic knowledge is unclear due to a lack of targeted evaluation gro…
cs.LG2026
Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective
Tokio Kajitsuka, Ukyo Honda, Sho Takase
Chain-of-thought (CoT) distillation transfers reasoning behaviors from a strong teacher to a smaller student, but prior work reports a capacity gap: distillation may fail when the…