Pith. sign in

REVIEW 6 cited by

EuroLLM-9B: Technical Report

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.04079 v2 pith:FX523G5Y submitted 2025-06-04 cs.CL cs.AIcs.LG

EuroLLM-9B: Technical Report

classification cs.CL cs.AIcs.LG
keywords eurollm-9beuropeanlanguagesincludinglanguageopendatadataset
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This report presents EuroLLM-9B, a large language model trained from scratch to support the needs of European citizens by covering all 24 official European Union languages and 11 additional languages. EuroLLM addresses the issue of European languages being underrepresented and underserved in existing open large language models. We provide a comprehensive overview of EuroLLM-9B's development, including tokenizer design, architectural specifications, data filtering, and training procedures. We describe the pre-training data collection and filtering pipeline, including the creation of EuroFilter, an AI-based multilingual filter, as well as the design of EuroBlocks-Synthetic, a novel synthetic dataset for post-training that enhances language coverage for European languages. Evaluation results demonstrate EuroLLM-9B's competitive performance on multilingual benchmarks and machine translation tasks, establishing it as the leading open European-made LLM of its size. To support open research and adoption, we release all major components of this work, including the base and instruction-tuned models, the EuroFilter classifier, and the synthetic post-training dataset.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation

    cs.CL 2026-04 unverdicted novelty 7.0

    Gemma 3 27B and Aya Expanse 32B are effective multilingual teachers; data qualities such as diversity and fluency explain over 93% of variance in student performance rather than model size.

  2. CARTE: A Benchmark for Mapping Language Model Knowledge Across France

    cs.CL 2026-06 unverdicted novelty 6.0

    CARTE is a new benchmark for fine-grained regional knowledge in France that shows LLMs exhibit performance gaps across regions and scales, pointing to uneven pretraining coverage.

  3. Is a Document Educational or Just Wikipedia-Style? -- Pitfalls of Classifier-Based Quality Filtering

    cs.CL 2026-05 unverdicted novelty 6.0

    Wikipedia-style reformatting reverses FineWeb-Edu CQF filtering decisions for ~7% of documents, admitting otherwise excluded low-quality content.

  4. Validity of LLMs as data annotators: AMALIA on authority

    cs.CL 2026-07 conditional novelty 5.0

    Portugal's 9B-parameter national language model AMALIA agrees with human annotators on coding moral authority but fails a construct-validity test showing it reaches correct codes via surface correlates rather than the...

  5. When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Illusions in LLMs

    cs.CL 2026-06 unverdicted novelty 5.0

    Dutch LLMs display coherence illusions tracked by surprisal, with attention entropy identifying affected heads and a new energy metric quantifying discourse coherence.

  6. Comparative Evaluation of Machine Translation Systems on Images with Text

    cs.CL 2026-05 unverdicted novelty 4.0

    Comparative evaluation on multilingual image-text datasets finds multi-modal LLMs outperform modular OCR+MT pipelines and an end-to-end model using BLEU, chrF, and TER.