evalSmarT: An LLM-Based Framework for Evaluating Smart Contract Generated Comments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Mbodji, Fatou Ndiaye
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913962388357120
author Mbodji, Fatou Ndiaye
author_facet Mbodji, Fatou Ndiaye
contents Smart contract comment generation has gained traction as a means to improve code comprehension and maintainability in blockchain systems. However, evaluating the quality of generated comments remains a challenge. Traditional metrics such as BLEU and ROUGE fail to capture domain-specific nuances, while human evaluation is costly and unscalable. In this paper, we present \texttt{evalSmarT}, a modular and extensible framework that leverages large language models (LLMs) as evaluators. The system supports over 400 evaluator configurations by combining approximately 40 LLMs with 10 prompting strategies. We demonstrate its application in benchmarking comment generation tools and selecting the most informative outputs. Our results show that prompt design significantly impacts alignment with human judgment, and that LLM-based evaluation offers a scalable and semantically rich alternative to existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20774
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle evalSmarT: An LLM-Based Framework for Evaluating Smart Contract Generated Comments
Mbodji, Fatou Ndiaye
Artificial Intelligence
Smart contract comment generation has gained traction as a means to improve code comprehension and maintainability in blockchain systems. However, evaluating the quality of generated comments remains a challenge. Traditional metrics such as BLEU and ROUGE fail to capture domain-specific nuances, while human evaluation is costly and unscalable. In this paper, we present \texttt{evalSmarT}, a modular and extensible framework that leverages large language models (LLMs) as evaluators. The system supports over 400 evaluator configurations by combining approximately 40 LLMs with 10 prompting strategies. We demonstrate its application in benchmarking comment generation tools and selecting the most informative outputs. Our results show that prompt design significantly impacts alignment with human judgment, and that LLM-based evaluation offers a scalable and semantically rich alternative to existing methods.
title evalSmarT: An LLM-Based Framework for Evaluating Smart Contract Generated Comments
topic Artificial Intelligence
url https://arxiv.org/abs/2507.20774