MétaCan
Menu
← Back to cohort
Record W4412886796 · doi:10.18653/v1/2025.acl-long.111

LLäMmlein: Transparent, Compact and Competitive German-Only Language Models from Scratch

2025· article· en· W4412886796 on OpenAlexaff
Jan Pfister, Julia Wunderle, Andreas Hotho

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsArtificial Intelligence in Medicine (Canada)
FundersJulius-Maximilians-Universität WürzburgDeutsche Forschungsgemeinschaft
KeywordsScratchGermanComputer scienceProgramming languageLinguisticsPhilosophy

Abstract

fetched live from OpenAlex

We transparently create two German-only decoder models, LLäMmlein 120M and 1B 1 , from scratch and publish them, along with training data, for the (German) NLP research community to use 2 .The model training involved several key steps, including data preprocessing/filtering, the creation of a German tokenizer, the training itself, as well as the evaluation of the final models on various benchmarks, also against existing models.Throughout the training process, multiple checkpoints were saved in equal intervals and analyzed using the German SuperGLEBer benchmark to gain insights into the models' learning process.Compared to state-of-the-art models on the SuperGLEBer benchmark, both LLäMmlein models performed competitively, consistently matching or surpassing models with similar parameter sizes.The results show that the models' quality scales with size as expected, but performance improvements on some tasks plateaued early during training, offering valuable insights into resource allocation for future models.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.005
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.013
Threshold uncertainty score0.044

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.005
Meta-epidemiology (narrow)0.0030.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.001
Scholarly communication0.0020.004
Open science0.0030.003
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0130.011

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.016
GPT teacher head0.303
Teacher spread0.287 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicNatural Language Processing Techniques→French-language works237,207→