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.
  • watch means 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

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.

Downloads last month
-
Safetensors
Model size
82.1M params
Tensor type
F32
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for aitrainingdatabroker/contract-clause-risk-classifier

Finetuned
(808)
this model

Dataset used to train aitrainingdatabroker/contract-clause-risk-classifier

Space using aitrainingdatabroker/contract-clause-risk-classifier 1