---
language:
- en
license: mit
library_name: transformers
tags:
- legal
- text-classification
- multi-label-classification
- terms-of-service
- unfair-clauses
datasets:
- coastalcph/lex_glue
base_model: microsoft/deberta-base
metrics:
- f1
- accuracy
pipeline_tag: text-classification
---

> ⚠️ **DEPRECATED** — This model used a non-standard training methodology (Focal Loss + class weighting) and was evaluated on a synthetic test set. For accurate, reproducible results on the official LexGLUE benchmark, use our updated models:
>
> | Model | μ-F1 | m-F1 |
> |-------|------|------|
> | **[lexglue-roberta-unfair-tos](https://huggingface.co/Agreemind/lexglue-roberta-unfair-tos)** | **96.1** | **84.4** |
> | [lexglue-legalbert-unfair-tos](https://huggingface.co/Agreemind/lexglue-legalbert-unfair-tos) | 96.0 | 84.1 |
> | [lexglue-deberta-unfair-tos](https://huggingface.co/Agreemind/lexglue-deberta-unfair-tos) | 95.6 | 82.2 |
> | [lexglue-legalbert-small-unfair-tos](https://huggingface.co/Agreemind/lexglue-legalbert-small-unfair-tos) | 95.0 | 78.5 |



# deberta-unfair-tos

Best performing model for UNFAIR-ToS classification

## Model Description

This model is fine-tuned on the [LexGLUE UNFAIR-ToS](https://huggingface.co/datasets/coastalcph/lex_glue) dataset to detect unfair clauses in Terms of Service documents.

**Base Model:** [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base)

## Performance

| Metric | Score |
|--------|-------|
| Exact Match Accuracy | 78.8% |
| Micro-F1 | 0.87 |
| Precision | 0.98 |

## Risk Categories

The model classifies text into 8 risk categories:

| ID | Category |
|----|----------|
| 0 | Limitation of liability |
| 1 | Unilateral termination |
| 2 | Unilateral change |
| 3 | Content removal |
| 4 | Contract by using |
| 5 | Choice of law |
| 6 | Jurisdiction |
| 7 | Arbitration |

## Usage

```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model_name = "Agreemind/deberta-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 = {deberta-unfair-tos},
  year = {2024},
  publisher = {HuggingFace},
  url = {https://huggingface.co/Agreemind/deberta-unfair-tos}
}
```