RAGSum couples retriever and generator in one CodeT5 model with contrastive pre-training, joint fine-tuning, and ROUGE-L based self-refinement, outperforming CMR-Sum, JOINTCOM, and Llama-3.1-8B on three code-comment datasets.
Deep code comment genera- tion,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Retriever Meets Generator: A Joint Model for Code Comment Generation
RAGSum couples retriever and generator in one CodeT5 model with contrastive pre-training, joint fine-tuning, and ROUGE-L based self-refinement, outperforming CMR-Sum, JOINTCOM, and Llama-3.1-8B on three code-comment datasets.