Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2507.12558 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908463512158208 |
|---|---|
| author | Le, Tien P. T. Bui, Anh M. T. Pham, Huy N. D. Bucaioni, Alessio Nguyen, Phuong T. |
| author_facet | Le, Tien P. T. Bui, Anh M. T. Pham, Huy N. D. Bucaioni, Alessio Nguyen, Phuong T. |
| contents | Automatically generating concise, informative comments for source code can lighten documentation effort and accelerate program comprehension. Retrieval-augmented approaches first fetch code snippets with existing comments and then synthesize a new comment, yet retrieval and generation are typically optimized in isolation, allowing irrelevant neighbors topropagate noise downstream. To tackle the issue, we propose a novel approach named RAGSum with the aim of both effectiveness and efficiency in recommendations. RAGSum is built on top offuse retrieval and generation using a single CodeT5 backbone. We report preliminary results on a unified retrieval-generation framework built on CodeT5. A contrastive pre-training phase shapes code embeddings for nearest-neighbor search; these weights then seed end-to-end training with a composite loss that (i) rewards accurate top-k retrieval; and (ii) minimizes comment-generation error. More importantly, a lightweight self-refinement loop is deployed to polish the final output. We evaluated theframework on three cross-language benchmarks (Java, Python, C), and compared it with three well-established baselines. The results show that our approach substantially outperforms thebaselines with respect to BLEU, METEOR, and ROUTE-L. These findings indicate that tightly coupling retrieval and generationcan raise the ceiling for comment automation and motivateforthcoming replications and qualitative developer studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_12558 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | When Retriever Meets Generator: A Joint Model for Code Comment Generation Le, Tien P. T. Bui, Anh M. T. Pham, Huy N. D. Bucaioni, Alessio Nguyen, Phuong T. Software Engineering Automatically generating concise, informative comments for source code can lighten documentation effort and accelerate program comprehension. Retrieval-augmented approaches first fetch code snippets with existing comments and then synthesize a new comment, yet retrieval and generation are typically optimized in isolation, allowing irrelevant neighbors topropagate noise downstream. To tackle the issue, we propose a novel approach named RAGSum with the aim of both effectiveness and efficiency in recommendations. RAGSum is built on top offuse retrieval and generation using a single CodeT5 backbone. We report preliminary results on a unified retrieval-generation framework built on CodeT5. A contrastive pre-training phase shapes code embeddings for nearest-neighbor search; these weights then seed end-to-end training with a composite loss that (i) rewards accurate top-k retrieval; and (ii) minimizes comment-generation error. More importantly, a lightweight self-refinement loop is deployed to polish the final output. We evaluated theframework on three cross-language benchmarks (Java, Python, C), and compared it with three well-established baselines. The results show that our approach substantially outperforms thebaselines with respect to BLEU, METEOR, and ROUTE-L. These findings indicate that tightly coupling retrieval and generationcan raise the ceiling for comment automation and motivateforthcoming replications and qualitative developer studies. |
| title | When Retriever Meets Generator: A Joint Model for Code Comment Generation |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2507.12558 |