Paper
TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation
Authors
Toms Bergmanis, Martins Kronis, Ingus Jānis Pretkalniņš, Dāvis Nicmanis, Jeļizaveta Jeļinska, Roberts Rozis, Rinalds Vīksna, Mārcis Pinnis
Abstract
Large language models often underperform in many European languages due to the dominance of English and a few high-resource languages in training data. This paper presents TildeOpen LLM, a 30-billion-parameter open-weight foundational model trained for 34 European languages to promote linguistic equity and improve performance for low-resource languages. To address the data imbalance, we combine dataset upsampling with a curriculum-based training schedule that alternates between uniform and natural language distributions. The resulting model performs favorably compared to other multilingual LLMs despite being trained with significantly fewer computing resources. Evaluation across multiple multilingual benchmarks shows that TildeOpen surpasses existing open-weight models in text generation and comprehension, particularly for Baltic, Finno-Ugric, and Slavic languages. Human evaluations confirm an up to tenfold reduction in linguistic errors relative to leading baselines. The model and associated resources are fully open-weight and publicly available at huggingface.co/TildeAI/TildeOpen-30b. These outcomes demonstrate that careful data curation and balanced training strategies can substantially enhance multilingual model quality without increasing model size or training volume.
Metadata
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.08182v1</id>\n <title>TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation</title>\n <updated>2026-03-09T10:03:17Z</updated>\n <link href='https://arxiv.org/abs/2603.08182v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.08182v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Large language models often underperform in many European languages due to the dominance of English and a few high-resource languages in training data. This paper presents TildeOpen LLM, a 30-billion-parameter open-weight foundational model trained for 34 European languages to promote linguistic equity and improve performance for low-resource languages. To address the data imbalance, we combine dataset upsampling with a curriculum-based training schedule that alternates between uniform and natural language distributions. The resulting model performs favorably compared to other multilingual LLMs despite being trained with significantly fewer computing resources. Evaluation across multiple multilingual benchmarks shows that TildeOpen surpasses existing open-weight models in text generation and comprehension, particularly for Baltic, Finno-Ugric, and Slavic languages. Human evaluations confirm an up to tenfold reduction in linguistic errors relative to leading baselines. The model and associated resources are fully open-weight and publicly available at huggingface.co/TildeAI/TildeOpen-30b. These outcomes demonstrate that careful data curation and balanced training strategies can substantially enhance multilingual model quality without increasing model size or training volume.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <published>2026-03-09T10:03:17Z</published>\n <arxiv:comment>LREC 2026</arxiv:comment>\n <arxiv:primary_category term='cs.CL'/>\n <author>\n <name>Toms Bergmanis</name>\n </author>\n <author>\n <name>Martins Kronis</name>\n </author>\n <author>\n <name>Ingus Jānis Pretkalniņš</name>\n </author>\n <author>\n <name>Dāvis Nicmanis</name>\n </author>\n <author>\n <name>Jeļizaveta Jeļinska</name>\n </author>\n <author>\n <name>Roberts Rozis</name>\n </author>\n <author>\n <name>Rinalds Vīksna</name>\n </author>\n <author>\n <name>Mārcis Pinnis</name>\n </author>\n </entry>"
}