卢森堡语口语问答新突破，用TTS增强数据实现低资源语言语音交互。
arXiv:2607.02763v1 Announce Type: new Abstract: Spoken Question Answering (SQA) remains largely focused on high-resource languages and carefully recor…
面向低资源语言罗马尼亚语的多模态指令微调，用参数高效方法实现视觉语言模型适配，填补非英语VLM研究空白。
arXiv:2512.14926v2 Announce Type: replace-cross Abstract: Focusing on low-resource languages is an essential step toward democratizing generative AI. …
揭露低资源语言与混合代码切换可绕过LLM安全防护，揭示模型安全泛化的关键漏洞。
arXiv:2607.01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncert…
卢森堡语大模型指令调优数据集LuxIT正式开源，独创单语种子数据高效构建方案，为低资源语言NLP突破奠定基础。
arXiv:2510.24434v3 Announce Type: replace Abstract: The effectiveness of instruction-tuned Large Language Models (LLMs) is often limited in low-resour…
提出QVal框架，低成本评估长程LLM代理的密集监督信号，提升任务效率。
arXiv:2606.32034v1 Announce Type: cross Abstract: LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or th…
首个阿拉伯语-俄语平行语料库与LLM基准，打破科研语言壁垒，助力可持续发展知识交流。
arXiv:2606.30943v1 Announce Type: new Abstract: Russian and Arabic are among the major languages of scientific communication. Language barriers impede…
探究数据混合与模型架构对非洲语言持续预训练的影响，为低资源语言建模提供前沿实证与设计指南。
arXiv:2601.06395v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly multilingual, yet open models continue to underperfo…
大模型在非洲低资源语言豪萨语和丰贝语上的翻译表现如何？新基准测试揭示失败模式与评估指标可靠性。
arXiv:2606.22269v1 Announce Type: cross Abstract: We investigate the translation quality of current large language models (LLMs) for English-to-Hausa …
本地运行、仅需160MB内存的Rust自然语言理解引擎，无需GPU和网络，毫秒级响应
Sophia NLU is an on device, low compute, Rust based natural language understanding engine that acts as a conversation agent. It offers the fluidity of…
探索提示工程在低资源语言乌克兰语上的语法纠错极限，揭示大模型与提示策略的边界。
arXiv:2606.09334v1 Announce Type: new Abstract: Fine-tuned Large Language Models (LLMs) dominate in Ukrainian grammatical error correction (GEC), whil…
基于语言模型的两阶段框架，破解低资源与濒危语言扫描词典的数字化难题
arXiv:2606.09435v1 Announce Type: new Abstract: Multilingual dictionaries are among the most valuable documentary resources for low-resource and endan…
利用通用数据解决低资源领域大模型适配难题，为领域迁移提供新思路
arXiv:2511.07380v2 Announce Type: replace Abstract: Adapting large language models (LLMs) to low-resource domains remains challenging due to the scarc…
仅26MB内存的Rust编码代理，对比JS代理节省超95%资源，极低功耗运行5种工作模式。
Article URL: https://gi-dellav.github.io/zerostack/ Comments URL: https://news.ycombinator.com/item?id=48401040 Points: 2 # Comments: 0
探索非洲语言自然语言推理的提示策略，为低资源NLI提供新思路
arXiv:2606.03304v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated in multilingual settings, yet their inference …
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…
边缘端语音识别模型微调覆盖19种非洲语言，突破低资源语种技术瓶颈
arXiv:2606.02375v1 Announce Type: new Abstract: We evaluate whether compact domain-specialized ASR models can outperform massively multilingual founda…
专为土耳其语优化的BERT模型SindBERT，填补低资源语言NLP空白
arXiv:2510.21364v2 Announce Type: replace Abstract: Transformer models have revolutionized NLP, yet many morphologically rich languages remain underre…
覆盖350种语言的单语模型Goldfish，大幅提升低资源语言NLP能力。
arXiv:2408.10441v3 Announce Type: replace Abstract: For many low-resource languages, the only available language models are large multilingual models …
罗马尼亚语视觉语言模型的构建指南，教你如何为低资源语言打造多模态AI。
arXiv:2605.31401v1 Announce Type: new Abstract: Vision-Language Models (VLMs) largely follow the text-only LLM trajectory, excelling on English benchm…
首个孟加拉语大模型多任务幻觉评估框架，填补低资源语言评测空白
arXiv:2605.31483v1 Announce Type: new Abstract: Despite Bengali being the sixth most spoken language in the world, no prior work has systematically ev…