|国家预印本平台
首页|cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree

cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree

cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree

来源:Arxiv_logoArxiv
英文摘要

Retrieval-Augmented Generation (RAG) has become essential for large-scale code generation, grounding predictions in external code corpora to improve actuality. However, a critical yet underexplored aspect of RAG pipelines is chunking -- the process of dividing documents into retrievable units. Existing line-based chunking heuristics often break semantic structures, splitting functions or merging unrelated code, which can degrade generation quality. We propose chunking via Abstract Syntax Trees (\ourwork), a structure-aware method that recursively breaks large AST nodes into smaller chunks and merges sibling nodes while respecting size limits. This approach generates self-contained, semantically coherent units across programming languages and tasks, improving performance on diverse code generation tasks, e.g., boosting Recall@5 by 4.3 points on RepoEval retrieval and Pass@1 by 2.67 points on SWE-bench generation. Our work highlights the importance of structure-aware chunking for scaling retrieval-enhanced code intelligence.

Yilin Zhang、Xinran Zhao、Zora Zhiruo Wang、Chenyang Yang、Jiayi Wei、Tongshuang Wu

计算技术、计算机技术

Yilin Zhang,Xinran Zhao,Zora Zhiruo Wang,Chenyang Yang,Jiayi Wei,Tongshuang Wu.cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree[EB/OL].(2025-06-18)[2025-06-29].https://arxiv.org/abs/2506.15655.点此复制

评论