Document automation improved by mixing classic rules with AI tools
In With the Old: Enhancing 'Classical' Document Automation with Generative AI
Artificial IntelligenceComputation and Language
Summary
It can be hard to automate creating legal documents using only traditional software because people’s writing is often unclear or incorrect. The authors show how combining older rule-based systems with newer AI that can understand and fix text problems helps make better legal document automation tools. Their early experiments involved using large language models to spot and correct issues in texts written by everyday users. This approach may make legal assistance software more effective and easier to use.
What this means in practice
- •For legal software developers: Enhance legal document automation by integrating rule-based systems with AI text fixes for clearer outputs from user inputs.
- •For customer support teams: Use AI to identify and correct text problems in customer-generated queries or forms for faster and more accurate handling.
Authors
Marc Lauritsen, Hannes Westermann
Abstract
Software-based legal assistance systems have leveraged many different forms of knowledge representation and reasoning. This article explores how document automation services rooted in expert system style and other symbolic approaches can usefully enhance and be enhanced by current generative AI approaches. We discuss the possible benefits and challenges, and report on preliminary experiments in using large language models to identify and fix issues in texts written by laypeople.