Automating construction contract review using knowledge graph-enhanced large language models

TL;DR

This paper presents a novel approach combining Large Language Models and Knowledge Graphs to automate and improve the accuracy and interpretability of construction contract review, addressing limitations of existing NLP methods.

Contribution

It introduces a tuning-free framework integrating LLMs with a Nested Contract Knowledge Graph using GraphRAG for enhanced contract risk identification.

Findings

Achieves more accurate risk evaluation than baseline models

Provides interpretable risk summaries

Demonstrates effectiveness on international EPC contracts

Abstract

An effective and efficient review of construction contracts is essential for minimizing construction projects losses, but current methods are time-consuming and error-prone. Studies using methods based on Natural Language Processing (NLP) exist, but their scope is often limited to text classification or segmented label prediction. This paper investigates whether integrating Large Language Models (LLMs) and Knowledge Graphs (KGs) can enhance the accuracy and interpretability of automated contract risk identification. A tuning-free approach is proposed that integrates LLMs with a Nested Contract Knowledge Graph (NCKG) using a Graph Retrieval-Augmented Generation (GraphRAG) framework for contract knowledge retrieval and reasoning. Tested on international EPC contracts, the method achieves more accurate risk evaluation and interpretable risk summaries than baseline models. These findings demonstrate the potential of combining LLMs and KGs for reliable reasoning in tasks that are knowledge-intensive and specialized, such as contract review.