Retrieval-Augmented Fine-Tuning for Improving Retrieve-and-Edit Based Assertion Generation

This repository serves as the open-source package for the paper Retrieval-Augmented Fine-Tuning for Improving Retrieve-and-Edit Based Assertion Generation. The Code folder includes all necessary scripts, modules, and configuration files for reproducing and extending the experiments presented in the paper, while the Data folder houses the associated datasets, trained models, and results.

本仓库为论文《用于改进基于检索-编辑的断言生成的检索增强微调（Retrieval-Augmented Fine-Tuning）》的开源工具包。代码目录包含了复现并拓展论文中所述实验所需的全部脚本、模块与配置文件；数据目录则存放了相关数据集、已训练模型及实验结果。