Replication package for "RAG-Reviewer: A Retrieval-Augmented Generation Framework for Automated Code Review Comment Generation"

This repository contains artifacts for the experiments described in RQ1~RQ3.fine_tuned_checkpoints.zipCheckpoints for each experimental run. Each folder follows the naming convention:modelName_ragStrategy_finetuned_best_ckp_epoch, where:modelName refers to the backbone model (e.g., CodeT5, CodeReviewer).ragStrategy denotes the prompting strategy: rag_pair, rag_singleton, or vanilla.epoch indicates the best-performing epoch based on validation performance.code_embeddings.zipVector embeddings of source code from the Tufano et al. dataset (train/val/test splits).Embeddings are stored as .pkl files and used for retrieval tasks.rag_candidate.zipContains the top-K most similar training examples for each instance in the train, validation, and test sets.These candidates were selected using semantic similarity for retrieval-augmented generation (RAG).The source code for reproducing these experiments is available on GitHub:https://github.com/RAG-Reviewer/RAG-Reviewer