Work

The Role of Prompt Patterns in LLM-Based Smart Contract Vulnerability Detection

Year: 2026
Type: conference-paper
Abstract: Smart contracts are immutable programs deployed on blockchain platforms, and their vulnerabilities can cause severe financial losses. Therefore, several tools have been proposed to detect these vulnerabilities. Among them, recent research has increasingly leveraged Large Language Models (LLMs) relying on carefully crafted prompts. Meanwhile, prior work has identified several prompt patterns, such as persona roles, chain-of-thought reasoning, and multi-agent interactions. However, the sensitivity of LLM performance to prompt design raises questions about the reliability of existing evaluations.
Language: English
Open Access status: gold
OpenAlex ID: W7204635274
FWCI: 1.323
Cites: 38
Cited by: 1
Related to: 10