揭示低资源语言在向量空间中的几何结构，为多语言模型优化提供全新视角。
arXiv:2608.23358v1 Announce Type: new Abstract: The performance gap between low- and high-resource languages in LLMs is widely known, but it remains u…
越南语六大方言实测大模型鲁棒性，多语言能力短板一目了然。
arXiv:2608.10414v1 Announce Type: cross Abstract: Large Language Models (LLMs) are typically evaluated on standard written Vietnamese, yet everyday co…
非营利组织打造的开放AI网络，免费提供多语言模型与API，助力AI民主化与全球普及。
Current AI, a non-profit building AI that leaves no one culture behind, has made remarkable progress across devices, AI chat and more.
跨语言迁移效果与语系亲疏直接挂钩，揭示多语言语音识别的隐藏规律
arXiv:2607.04814v1 Announce Type: cross Abstract: Extending automatic speech recognition (ASR) to low-resource African languages is constrained by the…
软令牌对齐解决跨语言推理错位难题，多语言模型表现更稳更聪明。
arXiv:2606.26466v1 Announce Type: new Abstract: Multilingual large language models often produce inconsistent reasoning and answers for semantically e…
从统计视角重新审视跨语言模型的表现差距，为多语言NLP提供新洞见。
arXiv:2510.15551v2 Announce Type: replace-cross Abstract: Any piece of knowledge is usually expressed in one or a handful of natural languages on the …
揭示大语言模型中隐藏的跨语言分布偏差，用“Shibboleth效应”审计多语言不平等现象。
arXiv:2606.11082v1 Announce Type: new Abstract: This study investigates cross-lingual distributional skew (the Shibboleth Effect) in frontier large la…
揭示低资源语言模型在多轮、多语言、多阶段训练中的新缩放定律，为高效预训练提供理论指导与实践依据。
arXiv:2410.12325v2 Announce Type: replace Abstract: In this paper, we study a fundamental design problem in pretraining Large Language Models (LLMs) f…
从结构视角解析大模型的多语言能力，揭示语言间共性与差异的深层机制。
arXiv:2606.01800v1 Announce Type: cross Abstract: Large language models (LLMs) have excelled in processing multiple languages through pre- and post-tr…
语言模型如何在不同文字间做出选择？这篇论文揭示了模型内部的“拉丁基底”机制。
arXiv:2605.31363v1 Announce Type: new Abstract: Many languages are written in multiple scripts, requiring large language models (LLMs) to generate equ…
ICML 2026录用论文：提出语言路由新方法，解决多语言策略优化中的语言分配问题，提升多模型协作效率。
arXiv:2605.25360v1 Announce Type: new Abstract: Large language models~(LLMs) are trained on heterogeneous multilingual corpora, yet existing policy op…
面向印地语的医学推理激励方案，探索大语言模型在低资源语言场景的深度应用
arXiv:2605.24635v1 Announce Type: new Abstract: Medical large language models hold promise for reducing healthcare disparities, yet Hindi remains seve…