metadata
language:
- pl
base_model:
- allegro/plt5-base
datasets:
- scilons/SciLaD-all-text-v1
library_name: transformers
tags:
- t5
- seq2seq
- text-to-text
- scientific-language-models
- cross-lingual-transfer
- wechsel
- global-mmlu
PL-Base-CP
Polish monolingual base model continued on the SciLaD target-language split as a 15k-step control baseline.
Model Details
This is a monolingual continued-pretraining control checkpoint reported in the paper table. It is provided for reproducibility of the baseline comparison.
- Paper name:
PL-Base-CP - Model role:
baseline-control - Source/base model: allegro/plt5-base
- Code and pipeline: GitHub repository
- Architecture: T5 encoder-decoder
- SciLaD dataset: scilons/SciLaD-all-text-v1
- Evaluation benchmark: Global-MMLU
Evaluation
Zero-shot Global-MMLU accuracy reported by the paper aggregation:
| Metric | Accuracy |
|---|---|
| Average | 24.65 |
| STEM | 23.88 |
| Humanities | 24.51 |
| Social Sciences | 23.43 |
| Other | 26.87 |
Limitations
The model is evaluated primarily with zero-shot Global-MMLU. Downstream task-specific evaluation is recommended before deployment in specialized scientific workflows.
Citation
- Title: Transferring Scientific English Pre-Trained Language Models to Multiple Languages Using Cross-Lingual Transfer
- Authors: Nikolas Rauscher, Fabio Barth, Georg Rehm
- Venue: LREC-COLING 2026, citation details TBA after publication