TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publication References
  4. An AI-powered auto-completion tool for Solidity smart contracts
 
Options

An AI-powered auto-completion tool for Solidity smart contracts

Publikationstyp
Conference Paper
Date Issued
2025-10
Sprache
English
Author(s)
Hensel, Fabian
Data Engineering E-19  
Banerjee, Avik 
Christian Doppler Forschungsgesellschaft  
Ebrahimi, Elmira 
Christian Doppler Forschungsgesellschaft  
Schulte, Stefan  
Christian Doppler Forschungsgesellschaft  
TORE-URI
https://hdl.handle.net/11420/60391
Start Page
171
End Page
180
Citation
IEEE International Conference on Blockchain, Blockchain 2025
Contribution to Conference
IEEE International Conference on Blockchain, Blockchain 2025  
Publisher DOI
10.1109/blockchain67634.2025.00031
Publisher
IEEE
ISBN of container
979-8-3315-9016-1
979-8-3315-9015-4
Solidity smart contracts are widely used to implement decentralized applications. However, their development remains challenging due to the language’s domain-specific complexity, the immutability of deployed contracts, which prevents post-deployment fixes, and the high risk of introducing security-critical vulnerabilities. While Large Language Models (LLMs) have advanced code generation across general domains, they often struggle to meet the structural and security-specific demands of smart contract development. Therefore, this paper presents a domain-adapted code completion model trained on 22,000 labeled code constructs extracted from Solidity contracts. The model is built on a transformer-based architecture and fine-tuned using Quantized Low-Rank Adaptation (QLoRA), a parameter-efficient method. The dataset is processed to highlight secure coding patterns and structural semantics, enabling the model to learn from both preceding and succeeding contexts. Evaluation using perplexity, the Bilingual Evaluation Understudy (BLEU) score, and the Metric for Evaluation of Translation with Explicit Ordering (METEOR) shows significant improvements with consistent gains across all three metrics compared to the base model. These results demonstrate that targeted adaptation of language models can significantly enhance coding support in Solidity smart contracts.
Subjects
blockchain
solidity
smart contracts
code completion
large language models
DDC Class
005.7: Data
TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback