EPS
← All batches·2605.15613

Toward LLMs Beyond English-Centric Development

topic: current_projecttop score: 100released: 2026-05-18first surfaced: 2026-05-18arXivPDFthreats2026-05-18

Authors: Sho Takase, Ukyo Honda

arXiv · PDF

Summary

arXiv:2605. 15613v1 Announce Type: new Abstract: Through an analysis of sequences generated by open-weight large language models (LLMs), we demonstrate that LLMs are heavily biased toward English.

Relevance

Read next because Toward LLMs Beyond English-Centric Development overlaps with clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)", clean result "Training one persona to emit a [ZLT] marker without bystanders adopting it has a one-cell-wide LR x epochs window on Qwen2.5-7B-Instruct (LOW confidence)", clean result "The marker is a representational handle, not a behavioural one — sharing it between a villain persona and the assistant transfers no misalignment (HIGH confidence)". Matching terms: under, source, rate, does, language, model. Source: arxiv cs.CL (NLP).

Threat model

Potential threat/caveat for clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)": this item discusses bias.

Abstract

arXiv:2605.15613v1 Announce Type: new Abstract: 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.