Efficacy of Various Large Language Models in Generating Smart Contracts

Siddhartha Chatterjee; Bina Ramamurthy

doi:10.1007/978-3-031-85363-0_31

Efficacy of Various Large Language Models in Generating Smart Contracts

Siddhartha Chatterjee
, Bina Ramamurthy

Department of Computer Science and Engineering

Mountain View High School

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

This study analyzes the application of code-generating Large Language Models in the creation of immutable Solidity smart contracts on the Ethereum Blockchain. Other works have previously analyzed Artificial Intelligence code generation abilities. This study aims to expand this to a larger scope to include programs where security and efficiency are of utmost priority such as smart contracts. The hypothesis leading into the study was that LLMs in general would have difficulty in rigorously implementing security details in the code, which was shown through our results, but surprisingly generally succeeded in many common types of contracts. We also discovered a novel way of generating smart contracts through new prompting strategies.

Original language	English
Title of host publication	Advances in Information and Communication - Proceedings of the 2025 Future of Information and Communication Conference, FICC 2025
Editors	Kohei Arai
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	482-500
Number of pages	19
ISBN (Print)	9783031853623
DOIs	https://doi.org/10.1007/978-3-031-85363-0_31
State	Published - 2025
Event	Future of Information and Communication Conference, FICC 2025 - Berlin, Germany Duration: Apr 28 2025 → Apr 29 2025

Publication series

Name	Lecture Notes in Networks and Systems
Volume	1284 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	Future of Information and Communication Conference, FICC 2025
Country/Territory	Germany
City	Berlin
Period	04/28/25 → 04/29/25

Keywords

Code generation
LLMs
Smart contract

Access to Document

10.1007/978-3-031-85363-0_31

Cite this

Chatterjee, S., & Ramamurthy, B. (2025). Efficacy of Various Large Language Models in Generating Smart Contracts. In K. Arai (Ed.), Advances in Information and Communication - Proceedings of the 2025 Future of Information and Communication Conference, FICC 2025 (pp. 482-500). (Lecture Notes in Networks and Systems; Vol. 1284 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-85363-0_31

Chatterjee, Siddhartha ; Ramamurthy, Bina. / Efficacy of Various Large Language Models in Generating Smart Contracts. Advances in Information and Communication - Proceedings of the 2025 Future of Information and Communication Conference, FICC 2025. editor / Kohei Arai. Springer Science and Business Media Deutschland GmbH, 2025. pp. 482-500 (Lecture Notes in Networks and Systems).

@inproceedings{4a5d5be69db14841a73c3095d0bc7601,

title = "Efficacy of Various Large Language Models in Generating Smart Contracts",

abstract = "This study analyzes the application of code-generating Large Language Models in the creation of immutable Solidity smart contracts on the Ethereum Blockchain. Other works have previously analyzed Artificial Intelligence code generation abilities. This study aims to expand this to a larger scope to include programs where security and efficiency are of utmost priority such as smart contracts. The hypothesis leading into the study was that LLMs in general would have difficulty in rigorously implementing security details in the code, which was shown through our results, but surprisingly generally succeeded in many common types of contracts. We also discovered a novel way of generating smart contracts through new prompting strategies.",

keywords = "Code generation, LLMs, Smart contract",

author = "Siddhartha Chatterjee and Bina Ramamurthy",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.; Future of Information and Communication Conference, FICC 2025 ; Conference date: 28-04-2025 Through 29-04-2025",

year = "2025",

doi = "10.1007/978-3-031-85363-0\_31",

language = "English",

isbn = "9783031853623",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "482--500",

editor = "Kohei Arai",

booktitle = "Advances in Information and Communication - Proceedings of the 2025 Future of Information and Communication Conference, FICC 2025",

address = "Germany",

}

Chatterjee, S & Ramamurthy, B 2025, Efficacy of Various Large Language Models in Generating Smart Contracts. in K Arai (ed.), Advances in Information and Communication - Proceedings of the 2025 Future of Information and Communication Conference, FICC 2025. Lecture Notes in Networks and Systems, vol. 1284 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 482-500, Future of Information and Communication Conference, FICC 2025, Berlin, Germany, 04/28/25. https://doi.org/10.1007/978-3-031-85363-0_31

Efficacy of Various Large Language Models in Generating Smart Contracts. / Chatterjee, Siddhartha; Ramamurthy, Bina.
Advances in Information and Communication - Proceedings of the 2025 Future of Information and Communication Conference, FICC 2025. ed. / Kohei Arai. Springer Science and Business Media Deutschland GmbH, 2025. p. 482-500 (Lecture Notes in Networks and Systems; Vol. 1284 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Efficacy of Various Large Language Models in Generating Smart Contracts

AU - Chatterjee, Siddhartha

AU - Ramamurthy, Bina

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

PY - 2025

Y1 - 2025

N2 - This study analyzes the application of code-generating Large Language Models in the creation of immutable Solidity smart contracts on the Ethereum Blockchain. Other works have previously analyzed Artificial Intelligence code generation abilities. This study aims to expand this to a larger scope to include programs where security and efficiency are of utmost priority such as smart contracts. The hypothesis leading into the study was that LLMs in general would have difficulty in rigorously implementing security details in the code, which was shown through our results, but surprisingly generally succeeded in many common types of contracts. We also discovered a novel way of generating smart contracts through new prompting strategies.

AB - This study analyzes the application of code-generating Large Language Models in the creation of immutable Solidity smart contracts on the Ethereum Blockchain. Other works have previously analyzed Artificial Intelligence code generation abilities. This study aims to expand this to a larger scope to include programs where security and efficiency are of utmost priority such as smart contracts. The hypothesis leading into the study was that LLMs in general would have difficulty in rigorously implementing security details in the code, which was shown through our results, but surprisingly generally succeeded in many common types of contracts. We also discovered a novel way of generating smart contracts through new prompting strategies.

KW - Code generation

KW - LLMs

KW - Smart contract

UR - https://www.scopus.com/pages/publications/105001050785

U2 - 10.1007/978-3-031-85363-0_31

DO - 10.1007/978-3-031-85363-0_31

M3 - Conference contribution

AN - SCOPUS:105001050785

SN - 9783031853623

T3 - Lecture Notes in Networks and Systems

SP - 482

EP - 500

BT - Advances in Information and Communication - Proceedings of the 2025 Future of Information and Communication Conference, FICC 2025

A2 - Arai, Kohei

PB - Springer Science and Business Media Deutschland GmbH

T2 - Future of Information and Communication Conference, FICC 2025

Y2 - 28 April 2025 through 29 April 2025

ER -

Chatterjee S, Ramamurthy B. Efficacy of Various Large Language Models in Generating Smart Contracts. In Arai K, editor, Advances in Information and Communication - Proceedings of the 2025 Future of Information and Communication Conference, FICC 2025. Springer Science and Business Media Deutschland GmbH. 2025. p. 482-500. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-031-85363-0_31

Efficacy of Various Large Language Models in Generating Smart Contracts

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this