SCALM: Detecting Bad Practices in Smart Contracts Through LLMs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912864709640192 |
|---|---|
| author | Li, Zongwei Li, Xiaoqi Li, Wenkai Wang, Xin |
| author_facet | Li, Zongwei Li, Xiaoqi Li, Wenkai Wang, Xin |
| contents | As the Ethereum platform continues to mature and gain widespread usage, it is crucial to maintain high standards of smart contract writing practices. While bad practices in smart contracts may not directly lead to security issues, they do elevate the risk of encountering problems. Therefore, to understand and avoid these bad practices, this paper introduces the first systematic study of bad practices in smart contracts, delving into over 35 specific issues. Specifically, we propose a large language models (LLMs)-based framework, SCALM. It combines Step-Back Prompting and Retrieval-Augmented Generation (RAG) to identify and address various bad practices effectively. Our extensive experiments using multiple LLMs and datasets have shown that SCALM outperforms existing tools in detecting bad practices in smart contracts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_04347 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SCALM: Detecting Bad Practices in Smart Contracts Through LLMs Li, Zongwei Li, Xiaoqi Li, Wenkai Wang, Xin Computation and Language Artificial Intelligence As the Ethereum platform continues to mature and gain widespread usage, it is crucial to maintain high standards of smart contract writing practices. While bad practices in smart contracts may not directly lead to security issues, they do elevate the risk of encountering problems. Therefore, to understand and avoid these bad practices, this paper introduces the first systematic study of bad practices in smart contracts, delving into over 35 specific issues. Specifically, we propose a large language models (LLMs)-based framework, SCALM. It combines Step-Back Prompting and Retrieval-Augmented Generation (RAG) to identify and address various bad practices effectively. Our extensive experiments using multiple LLMs and datasets have shown that SCALM outperforms existing tools in detecting bad practices in smart contracts. |
| title | SCALM: Detecting Bad Practices in Smart Contracts Through LLMs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.04347 |