paper-with-me

Papers

Toward LLMs Beyond English-Centric Development

2026-05-15 · Sho Takase, Ukyo Honda arxiv

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 commonly used to adapt LLMs to a target language, we show that it does not offer a cost advantage over training from scratch, even for improving cultural understanding in the target language. These findings suggest that dedicated per-language investment may become increasingly important for future LLM development, rather than relying primarily on the expansion of English-centric resources.

📄 PDF Abstract BibTeX arXiv:2605.15613

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models

2024-03-15 · Chaoqun Liu, Wenxuan Zhang, Yiran Zhao, Anh Tuan Luu 외

Large language models (LLMs) have demonstrated multilingual capabilities, yet they are mostly English-centric due to the imbalanced training corpora. While prior works have leveraged this bias to enhance multilingual per…

AllMultilingual NLPTranslation

Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?

2024-08-20 · Chengzhi Zhong, Fei Cheng, Qianying Liu, Junfeng Jiang 외

In this study, we investigate whether non-English-centric LLMs, despite their strong performance, `think' in their respective dominant language: more precisely, `think' refers to how the representations of intermediate l…

Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models

2025-10-03 · Ej Zhou, Caiqi Zhang, Tiancheng Hu, Chengzu Li 외 arxiv

Confidence calibration, the alignment of a model's predicted confidence with its actual accuracy, is crucial for the reliable deployment of Large Language Models (LLMs). However, this critical property remains largely un…

PLLuM: A Family of Polish Large Language Models

2025-11-05 · Jan Kocoń, Maciej Piasecki, Arkadiusz Janz, Teddy Ferdinan 외 arxiv

Large Language Models (LLMs) play a central role in modern artificial intelligence, yet their development has been primarily focused on English, resulting in limited support for other languages. We present PLLuM (Polish …

Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models

2024-11-02 · Hongyuan Lu, Zixuan Li, Wai Lam

As current training data for Large Language Models (LLMs) are dominated by English corpus, they are English-centric and they present impressive performance on English reasoning tasks.\footnote{This paper primarily studie…

GSM8KMath