Contract Clause Risk Classifier
Reads one data license clause and says whether it looks standard or worth a closer look (watch), for example an exclusive grant with no end date, uncapped indemnity or no right to deletion.
Every name, number and sentence it was trained on is made up. Nothing comes from a real person, customer or business.
Related tool: contract-clause-watchlist (a Space that runs in your browser).
Why it exists
A first pass over a long agreement can flag the clauses a lawyer should read first. This model is that first pass.
Use it
from transformers import pipeline
classify = pipeline("text-classification", model="aitrainingdatabroker/contract-clause-risk-classifier", top_k=3)
print(classify("The license is perpetual and irrevocable and survives any breach by the Licensee."))
How it was trained
Fine-tuned from distilroberta-base for 6 epochs on one RTX 3070. Training data: 376 rows from synthetic-contract-clauses-by-type-and-risk, all invented, with test rows built from templates the model never saw in training. The scripts that built the data and trained the model are in source/; the full scores are in scores.json.
Test scores
On 186 held-out rows: accuracy 0.919, macro F1 0.919.
| Label | F1 | Count |
|---|---|---|
standard |
0.915 | 91 |
watch |
0.923 | 95 |
Limits
- Trained only on invented text from templates, with test sentences built from templates it never saw. Real text varies far more.
watchmeans look closer, not that a clause is unfair or unlawful. A clause that is fine in one deal can be a problem in another.- This model is not legal advice and not a certification. A person should review its output before anything is shared or decided, and your counsel decides what a rule requires.
Read more
- Who is liable when data is licensed to AI
- Buying structured datasets for AI
- How you get paid when you license data
License and credit
Apache 2.0. Please credit AI Training Data Broker and link to https://aitrainingdatabroker.com/ when you share or build on it.
About
AI Training Data Broker is a broker and technical advisor for companies that sell or license their data to AI labs. It guides the technical side, including export, format, de-identification and compliance, and publishes free guides, checklists and tools.