LEGIT BART

🚀 Model Card: LEGIT-BART Series

The LEGIT-BART models are a family of pre-trained transformer-based models designed for Italian legal text processing. They are built upon BART-IT and further pre-trained on Italian legal corpora, offering unique features for handling legal documents.

✨ Features

• Extended context length: With Local-Sparse-Global (LSG) Attention, it can handle up to 16,384 tokens, enabling more comprehensive analysis of legal texts.
• Trained on legal documents: The models are trained on statutes, case law, and contracts, making them well-suited for legal text processing.
• Not fine-tuned for specific tasks: They require further adaptation for specific legal NLP tasks.

📦 Available Models

🔧 Technical Details

Architecture

• Base Model: morenolq/bart-it
• Transformer Encoder-Decoder: Utilizes a standard encoder-decoder architecture for text processing.
• LSG Attention: Enables handling of long documents effectively.
• Specific tokenizers: Models trained from scratch use specific tokenizers, but they underperform in continual pre-training compared to other models.

Training Data

• Dataset: joelniklaus/Multi_Legal_Pile
• Types of legal texts: The models are trained on legislation, case law, and contracts, providing a comprehensive understanding of legal language.

💻 Usage Examples

Basic Usage

from transformers import BartForConditionalGeneration, AutoTokenizer

# Load tokenizer and model
model_name = "morenolq/LEGIT-BART"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = BartForConditionalGeneration.from_pretrained(model_name)

# Example input
input_text = "<mask> 1234: Il contratto si intende concluso quando..."
inputs = tokenizer(input_text, return_tensors="pt", max_length=512, truncation=True)

# Pre-trained model fill the mask
output_ids = model.generate(inputs.input_ids, max_length=150, num_beams=4, early_stopping=True)
output_text = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print("📝:", output_text)

⚠️ Important Note

• Not fine-tuned for specific tasks: The models are pre-trained on legal texts and may require further adaptation for specific legal NLP tasks (e.g., summarization, question-answering).
• Bias and fairness: Legal texts may contain biases present in the legal system. Care should be taken to ensure fairness and ethical use of the models.
• Legal advice: The models are not a substitute for professional legal advice. Always consult a qualified legal professional for legal matters.

📚 Documentation

The paper presenting LEGIT-BART models is currently under review and will be updated here once published.

@article{benedetto2025legitbart,
	title        = {LegItBART: a summarization model for Italian legal documents},
	author       = {Benedetto, Irene and La Quatra, Moreno and Cagliero, Luca},
	year         = 2025,
	journal      = {Artificial Intelligence and Law},
	publisher    = {Springer},
	pages        = {1--31},
	doi          = {10.1007/s10506-025-09436-y},
	url          = {doi.org/10.1007/s10506-025-09436-y}
}

📄 License

This model is released under the MIT license.