library_name: transformers
pipeline_tag: text-classification
language:
- cs
tags:
- legal
- modernbert
- czech
- legal-nlp
ModernBERT-large-madon-arg-detection
This model is a fine-tuned version of ModernBERT-large for Czech legal argument detection. It was introduced in the paper Mining Legal Arguments to Study Judicial Formalism.
The model is part of the MADON project, which focuses on detecting and classifying judicial reasoning in Czech court decisions. This specific model corresponds to Task 1 in the paper: detecting whether a paragraph in a legal decision is argumentative or non-argumentative.
Model Description
The model was adapted to the Czech legal domain through continued pretraining on a corpus of over 300,000 court decisions and fine-tuned on the MADON dataset. In the paper's evaluation, this model achieved a Balanced F1 score of 82.6% for argument detection.
- Paper: Mining Legal Arguments to Study Judicial Formalism
- Repository: TrustHLT/MADON
- Task: Binary text classification (argumentative vs. non-argumentative)
- Language: Czech
Usage
You can use this model for presence classification of Czech legal arguments using the transformers library:
from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
model = AutoModelForSequenceClassification.from_pretrained("TrustHLT/ModernBERT-large-madon-arg-detection")
tokenizer = AutoTokenizer.from_pretrained("TrustHLT/ModernBERT-large-madon-arg-detection")
pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
text = "This is a legal paragraph" # Replace with Czech legal text
print(pipe(text))
Citation
If you find this model useful, please cite:
@article{madon2025,
title={Mining Legal Arguments to Study Judicial Formalism},
author={Anonymous},
journal={arXiv preprint arXiv:2512.11374},
year={2025}
}