Business Impacts
Improved reviewer productivity by reducing redlining efforts by 60%
Enabled reviewers to find answers to 143 intricate contract questions with over 80% accuracy
Customer Key Facts
- Country : Canada
- Industry : HCLS
AI Assisted Contract Comparison
The customer, a leading healthcare provider based in Toronto, Canada, partnered with Quantiphi to develop an advanced contract redlining solution using generative AI. This solution is deployed in a user-friendly interface, allowing employees to cross-verify results and provide feedback.
Challenges
- Hundreds of hours spent weekly on manual contract analysis
- Low accuracy of contract comparisons due to manual errors
Technologies Used
Cloud Storage Bucket
Firestore
Elastic search
Vertex AI Workbench
Virtual Private Cloud
Cloud Run
Cloud Build
Cloud Functions
Cloud Task
GKE
Gitlab
Cloud CDN
Model Garden
Solution
Quantiphi proposed baioniq, our in-house generative AI platform for legal documents, capable of reading, ingesting, summarizing, and redlining contracts.
The project handled four types of contracts: Letter of Indemnification, Academic, Contract Research Organization, and Non-Contract Research Organization.
We developed a three-layer ML solution for redlining:
- Clause Extraction: Finetuned text-bison model to extract relevant clauses from contracts.
- Retriever: Built a retriever layer to extract the right clauses based on rules provided by the UH team.
- Redlining: Finetuned text-bison model to perform contract redlining.
Results
Quantiphi implemented a standard train, test, and evaluation strategy for our model, which is currently being tested by the customer on the UI. Preliminary results show 60-65% accuracy for the redlining layer, while the clause extraction and retriever layers achieve over 85% accuracy.
