REVIEW 10 cited by
Teuken-7B-Base & Teuken-7B-Instruct: Towards European LLMs
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
Signed reviews
read the original abstract
We present two multilingual LLMs, Teuken 7B-base and Teuken 7B-instruct, designed to embrace Europe's linguistic diversity by supporting all 24 official languages of the European Union. Trained on a dataset comprising around 60% non-English data and utilizing a custom multilingual tokenizer, our models address the limitations of existing LLMs that predominantly focus on English or a few high-resource languages. We detail the models' development principles, i.e., data composition, tokenizer optimization, and training methodologies. The models demonstrate strong performance across multilingual benchmarks, as evidenced by their performance on European versions of ARC, HellaSwag, and TruthfulQA.
Forward citations
Cited by 10 Pith papers
-
A Cartography of Open Collaboration in Open Source AI: Mapping Practices, Motivations, and Governance in 14 Open Large Language Model Projects
A qualitative interview study of 14 open LLM projects maps where collaboration happens, why developers participate, and how projects are governed across the model lifecycle.
-
Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian
Llama-GENBA-10B is a 10B-parameter trilingual model that reports top Bavarian scores among sub-10B models on a machine-translated benchmark the authors built.
-
MELABenchv1: Benchmarking Large Language Models against Smaller Fine-Tuned Models for Low-Resource Maltese NLP
A new 11-task Maltese benchmark shows that 55 large language models lag behind small fine-tuned models, with prior Maltese exposure the strongest predictor.
-
IberBench: LLM Evaluation on Iberian Languages
A community-run benchmark for Iberian languages shows that LLMs underperform on industry-relevant NLP tasks and on Basque and Galician relative to fundamental tasks and other Iberian languages.
-
A Sovereign, Open-Source Foundation Model for German and English
Soofi S 30B-A3B, a hybrid Mamba-MoE model pretrained on ~27T tokens with deliberately up-weighted German, reports the highest English and German aggregate scores among fully open base models in its comparison while ma...
-
Can Prompting LLMs Unlock Hate Speech Detection across Languages? A Zero-shot and Few-shot Study
Prompted LLMs beat fine-tuned encoders on HateCheck functional tests but trail them on real-world test sets across eight non-English languages.
-
DNB-AI-Project at SemEval-2025 Task 5: An LLM-Ensemble Approach for Automated Subject Indexing
An LLM ensemble with few-shot prompting and embedding-based vocabulary mapping achieves fourth place quantitatively and first place qualitatively in automated subject indexing at SemEval-2025 Task 5.
-
Salamandra Technical Report
Salamandra is an open, from-scratch multilingual LLM family with 2B, 7B, and 40B checkpoints, instruction-tuned variants, a vision proof-of-concept, and detailed evaluations across Iberian and European languages.
-
From Data to Device: ELMOD An Efficient German-First 2.7B Language Model for Mobile Inference
A 2.7B German-first LLM trained cheaply on public data with language-specific quality filtering matches larger 7B models on German reasoning benchmarks and runs on-device.
-
Bielik 11B v2 Technical Report
Bielik 11B v2, a depth-upscaled Mistral model continued-pretrained on Polish data, scores at or near the top of several Polish benchmarks despite having far fewer parameters than leading rivals.
Discussion (0). Continue with ORCID to comment.