from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model_name = "Agreemind/legalbert-large-unfair-tos"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

text = "We reserve the right to terminate your account at any time."
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)

with torch.no_grad():
    outputs = model(**inputs)
    probs = torch.sigmoid(outputs.logits)

# Get predictions
labels = ["Limitation of liability", "Unilateral termination", "Unilateral change", 
          "Content removal", "Contract by using", "Choice of law", "Jurisdiction", "Arbitration"]
          
for label, prob in zip(labels, probs[0]):
    if prob > 0.5:
        print(f"{label}: {prob:.2%}")

Training

Dataset: LexGLUE UNFAIR-ToS (~5,500 samples)
Loss: Focal Loss with class weighting
Optimizer: AdamW with cosine LR schedule
Epochs: 15 (with early stopping)

Limitations

Arbitration class has lower recall (~38%) due to limited training samples
Optimized for English legal text

Citation

bibtex

@misc{agreemind-unfair-tos,
  author = {Agreemind},
  title = {legalbert-large-unfair-tos},
  year = {2024},
  publisher = {HuggingFace},
  url = {https://huggingface.co/Agreemind/legalbert-large-unfair-tos}
}