Graph-based Keyword Planning for Legal Clause Generation from Topics

TL;DR

This paper introduces a controllable, graph-based method for generating legal clauses from minimal input topics, improving automation in legal document creation through a two-stage planning and generation pipeline.

Contribution

It presents a novel two-stage framework combining graph-based planning with clause generation for legal text, enabling topic-controlled clause creation.

Findings

Effective clause generation across diverse legal topics

Improved controllability in legal clause synthesis

Demonstrated success on contract clause datasets

Abstract

Generating domain-specific content such as legal clauses based on minimal user-provided information can be of significant benefit in automating legal contract generation. In this paper, we propose a controllable graph-based mechanism that can generate legal clauses using only the topic or type of the legal clauses. Our pipeline consists of two stages involving a graph-based planner followed by a clause generator. The planner outlines the content of a legal clause as a sequence of keywords in the order of generic to more specific clause information based on the input topic using a controllable graph-based mechanism. The generation stage takes in a given plan and generates a clause. The pipeline consists of a graph-based planner followed by text generation. We illustrate the effectiveness of our proposed two-stage approach on a broad set of clause topics in contracts.