针对 Solidity 智能合约错误检测的零样本推理方法基准测试

Smart contracts play a crucial role in blockchain systems by encoding financial and operational logic. However, their vulnerability to subtle security flaws poses significant risks of financial loss and erosion of trust. Large Language Models (LLMs) create new opportunities for automating vulnerability detection, yet the effectiveness of various prompting strategies and model choices in real-world contexts remains uncertain. This study evaluates state-of-the-art LLMs on Solidity smart contract analysis using a balanced dataset of 400 contracts across two tasks: (i) Error Detection, where the model performs binary classification to determine if a contract is vulnerable, and (ii) Error Classification, where the model must assign the predicted issue to a specific vulnerability type.