Problem
Research questions and friction points this paper is trying to address.
commit message generation
exemplar retrieval
large language models
VS Code extension
user feedback
CoRaCommit: A VS Code Extension for Commit Message Generation with Exemplar Retrieval
🤖 AI Summary
This work addresses the inefficiency and inconsistency of manually crafted commit messages and the limitations of existing tools in leveraging historical similar commits or incorporating user feedback for refinement. The authors propose a retrieval-augmented, multi-large language model (LLM) parallel generation approach that retrieves semantically similar historical commits to serve as contextual prompts, concurrently invokes multiple LLMs to produce candidate messages, and dynamically recommends the best-performing model based on user feedback. Implemented as a VS Code extension, the system integrates code diff analysis, similarity-based commit retrieval, and a feedback-driven learning mechanism. Experimental evaluation on 945 commits from the ApacheCM dataset demonstrates that the proposed method significantly outperforms state-of-the-art baselines across multiple automatic metrics, including BLEU, CIDEr, METEOR, and ROUGE-L.
📝 Abstract
Commit messages are essential textual artifacts that describe the intent behind code changes, and play a critical role in version control, code review, and historical tracking. However, in practice, commit messages are primarily authored manually, which is time-consuming and often results in inconsistent quality and non-uniform expression. Existing VS Code extensions for commit message generation typically directly invoke large language models based on the code diff, without leveraging similar commit exemplars as references, and rarely support user feedback-driven LLM recommendation. To address these limitations, this paper presents CoRaCommit, a VS Code extension that enhances commit message generation by retrieving similar commit exemplars as prompt context, invoking multiple LLMs in parallel for candidate commit message comparison, and dynamically recommending LLMs based on user feedback. Experimental results on 945 commits from the ApacheCM dataset show that CoRaCommit outperforms existing VS Code extensions across BLEU, CIDEr, METEOR, and ROUGE-L metrics, demonstrating the effectiveness of retrieval-augmented context for commit message generation.
Innovation
Methods, ideas, or system contributions that make the work stand out.
commit message generation
exemplar retrieval
large language models
user feedback
VS Code extension
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
