Systematic analysis of large language models for automating document-to-smart contract transformation

Abstract

Fragmentation and poor collaboration in contract-heavy industries hinder innovation. While smart contracts offer promising automation for digital documents, the transformation process presents significant challenges. Current approaches are promising but are often constrained by technical limitations, domain-specific requirements, and limited flexibility, restricting widespread adoption. This paper systematically reviews the development of smart contracts using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework to examine methodologies, challenges, and solutions through a thematic analysis of 30 key studies. The findings are grouped into three categories: Natural Language Processing (NLP)-based, template-based and ontology-based, and model-driven approaches. After analyzing the cross-industrial challenges of each category, this paper proposes a Large Language Model (LLM)-based smart contract generation solution to address the identified challenges validated through real-world use cases. This comprehensive analysis contributes to the ongoing dialogue on smart contracting, offering directions for future research and practical implementation in the digital infrastructure.