1
RUMBA: Russian User Memory Benchmark
首个俄语用户记忆基准RUMBA，专门评测大模型在俄语场景下的记忆力表现，填补非英语评估空白。
arXiv:2607.21447v1 Announce Type: cross Abstract: The ability to handle long-term memory in LLMs is becoming increasingly critical, yet existing bench…
2
Bridging Scientific Heritage: An Arabic--Russian Parallel Corpus and LLM Benchmark for Sustainable Knowledge Transfer
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…
3
A Komi-Yazva--Russian Parallel Corpus and Evaluation Protocol for Zero- and Few-Shot LLM Translation
首个科米-亚兹瓦语-俄语平行语料库，为LLM在极低资源语言上的零样本/少样本翻译提供系统评估标准。
arXiv:2606.06420v1 Announce Type: new Abstract: We present the first Komi-Yazva--Russian parallel corpus together with an explicit evaluation protocol…
4
Linked Multi-Model Data on Russian Domestic and Foreign Policy Speeches
多模态政治演讲数据集，覆盖俄罗斯政府内外政策讲话，提供俄语文本与图像，适合政治学与计算语言学研究
arXiv:2605.15886v1 Announce Type: new Abstract: This paper introduces a dataset of interlinked multimodal political communications from the Russian go…