Comparative Analysis of Solidity Smart Contract Generation Using Large Language Models Based on Formal Algebraic Specifications
This article presents a comparative analysis of automatic Solidity smart contract generation using large language models (LLMs) based on two approaches: natural language textual descriptions and formal algebraic specifications. The study analyzes smart contracts generated by LLMs (ChatGPT-4, Claude 3.7 Sonnet, DeepSeek-V3) as well as by the AI-based tool GitHub Copilot, evaluating their syntactic correctness, compliance with initial requirements, and security.