| --- |
| language: |
| - it |
| tags: |
| - text2text-generation |
| - summarization |
| - legal-ai |
| - italian-law |
| license: mit |
| datasets: |
| - joelniklaus/Multi_Legal_Pile |
| library_name: transformers |
| pipeline_tag: text2text-generation |
| widget: |
| - text: "<mask> 1234: Il contratto si intende concluso quando..." |
| base_model: |
| - morenolq/bart-it |
| --- |
| |
| # 📌 Model Card: LEGIT-BART Series |
|
|
| ## 🏛️ Model Overview |
| The **LEGIT-BART** models are a family of **pre-trained transformer-based models** for **Italian legal text processing**. |
| They build upon **BART-IT** ([`morenolq/bart-it`](https://huggingface.co/morenolq/bart-it)) and are further pre-trained on **Italian legal corpora**. |
|
|
| 💡 Key features: |
| - **Extended context length** with **Local-Sparse-Global (LSG) Attention** (up to **16,384 tokens**) 📜 |
| - **Trained on legal documents** such as **statutes, case law, and contracts** 📑 |
| - **Not fine-tuned for specific tasks** (requires further adaptation) |
|
|
| ## 📂 Available Models |
|
|
| | Model | Description | Link | |
| |--------|-------------|------| |
| | **LEGIT-BART** | Continued pre-training of `morenolq/bart-it` on **Italian legal texts** | [🔗 Link](https://huggingface.co/morenolq/LEGIT-BART) | |
| | **LEGIT-BART-LSG-4096** | Continued pre-training of `morenolq/bart-it`, supporting **4,096 tokens** | [🔗 Link](https://huggingface.co/morenolq/LEGIT-BART-LSG-4096) | |
| | **LEGIT-BART-LSG-16384** | Continued pre-training of `morenolq/bart-it`, supporting **16,384 tokens** | [🔗 Link](https://huggingface.co/morenolq/LEGIT-BART-LSG-16384) | |
| | **LEGIT-SCRATCH-BART** | Trained from scratch on **Italian legal texts** | [🔗 Link](https://huggingface.co/morenolq/LEGIT-SCRATCH-BART) | |
| | **LEGIT-SCRATCH-BART-LSG-4096** | Trained from scratch with **LSG attention**, supporting **4,096 tokens** | [🔗 Link](https://huggingface.co/morenolq/LEGIT-SCRATCH-BART-LSG-4096) | |
| | **LEGIT-SCRATCH-BART-LSG-16384** | Trained from scratch with **LSG attention**, supporting **16,384 tokens** | [🔗 Link](https://huggingface.co/morenolq/LEGIT-SCRATCH-BART-LSG-16384) | |
| | **BART-IT-LSG-4096** | `morenolq/bart-it` with **LSG attention**, supporting **4,096 tokens** (no legal adaptation) | [🔗 Link](https://huggingface.co/morenolq/BART-IT-LSG-4096) |
| | **BART-IT-LSG-16384** | `morenolq/bart-it` with **LSG attention**, supporting **16,384 tokens** (no legal adaptation) | [🔗 Link](https://huggingface.co/morenolq/BART-IT-LSG-16384) | |
|
|
| --- |
|
|
| ## 🛠️ Model Details |
|
|
| 🔹 **Architecture** |
| - Base Model: [`morenolq/bart-it`](https://huggingface.co/morenolq/bart-it) |
| - Transformer Encoder-Decoder |
| - **LSG Attention** for long documents |
| - Specific tokenizers for models trained from scratch (underperforming continual pre-training in our experiments). |
|
|
| 🔹 **Training Data** |
| - Dataset: [`joelniklaus/Multi_Legal_Pile`](https://huggingface.co/datasets/joelniklaus/Multi_Legal_Pile) |
| - Types of legal texts used: |
| - **Legislation** (laws, codes, amendments) |
| - **Case law** (judicial decisions) |
| - **Contracts** (public legal agreements) |
|
|
| --- |
|
|
| ## 🚀 How to Use |
|
|
| ```python |
| from transformers import BartForConditionalGeneration, AutoTokenizer |
| |
| # Load tokenizer and model |
| model_name = "morenolq/LEGIT-SCRATCH-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) |
| ``` |
|
|
| --- |
|
|
| ⚠️ Limitations & Ethical Considerations |
| - **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. |
|
|
| --- |
|
|
| ## 📚 Reference |
|
|
| The paper presenting LEGIT-BART models is currently under review and will be updated here once published. |
|
|
| ```bibtex |
| @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} |
| } |
| ``` |
|
|
| --- |
