iSEngLab/LLM4UT_Empirical

[ISSTA 2025] A Large-scale Empirical Study on Fine-tuning Large Language Models for Unit Testing

13
/ 100
Experimental

This repository provides a comprehensive study on how large language models (LLMs) can be optimized for generating effective unit tests, assertions, and for evolving existing tests. It offers the datasets and scripts needed to reproduce experiments, helping you understand how different LLMs perform and which methods (fine-tuning versus prompt engineering) are most effective. Software engineers and QA specialists can use this to guide their adoption of LLMs for improving software quality.

No commits in the last 6 months.

Use this if you are a software engineer or QA professional looking to leverage large language models to automate or enhance unit testing processes, and you want to understand the best practices and performance trade-offs.

Not ideal if you are looking for a ready-to-use tool to immediately generate unit tests without needing to understand or reproduce the underlying research.

Software Testing Unit Test Generation LLM Fine-tuning Software Quality Assurance Test Automation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

13

Forks

Language

Python

License

Last pushed

Feb 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/iSEngLab/LLM4UT_Empirical"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.