Construction contract risk identification based on knowledge-augmented language model

TL;DR

This paper introduces a knowledge-augmented, tuning-free large language model approach for more effective and reliable construction contract risk identification, improving upon traditional review methods by incorporating domain-specific knowledge.

Contribution

It presents a novel, tuning-free method that integrates construction contract knowledge into large language models to emulate expert contract review processes.

Findings

Achieved solid performance on real construction contracts

Enhanced risk identification accuracy with domain knowledge integration

Provided insights into LLM logical reasoning during contract review

Abstract

Contract review is an essential step in construction projects to prevent potential losses. However, the current methods for reviewing construction contracts lack effectiveness and reliability, leading to time-consuming and error-prone processes. While large language models (LLMs) have shown promise in revolutionizing natural language processing (NLP) tasks, they struggle with domain-specific knowledge and addressing specialized issues. This paper presents a novel approach that leverages LLMs with construction contract knowledge to emulate the process of contract review by human experts. Our tuning-free approach incorporates construction contract domain knowledge to enhance language models for identifying construction contract risks. The use of a natural language when building the domain knowledge base facilitates practical implementation. We evaluated our method on real construction contracts and achieved solid performance. Additionally, we investigated how large language models employ logical thinking during the task and provide insights and recommendations for future research.