Replication Package of the Paper: "Using Large Language Models for Commit Message Generation: A Preliminary Study"

This replication package contains the evaluation data and script files used in the paper "Using Large Language Models for Commit Message Generation: A Preliminary Study". We provide below a brief description of each folder: experiment_data/human_evaluation: Human evaluation results from two participants. experiment_data/msg: Generated commit messages of each method (baselines & LLMs) and human-written commit messages. script: Evaluation metric script, parallel inference script (for using OpenAI API).