Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.19033 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911200099434496 |
|---|---|
| author | Dong, Qian Chen, Jia Ai, Qingyao Wang, Hongning Li, Haitao Wu, Yi Hu, Yao Liu, Yiqun Ma, Shaoping |
| author_facet | Dong, Qian Chen, Jia Ai, Qingyao Wang, Hongning Li, Haitao Wu, Yi Hu, Yao Liu, Yiqun Ma, Shaoping |
| contents | Existing retrieval-augmented code generation (RACG) methods typically use an external retrieval module to fetch semantically similar code snippets used for generating subsequent fragments. However, even for consecutive code fragments, the content often diverges due to logical progression, resulting in a content gap. This gap undermines the performance of current RACG methods, as \textit{external} retrieval modules based on content matching fail to infer the specific information need of LLMs to generate the next code fragment. Therefore, we propose \textbf{SelfRACG}, a novel paradigm that enables large language models (LLMs) to \textbf{Self}-express their information needs to enhance \textbf{RACG}. Specifically, SelfRACG includes an information need expression module and a two-stage information need-guided training strategy, which encourages LLMs to express their information need. Extensive experiments demonstrate that SelfRACG can retrieve external knowledge that better aligns with the LLM's own information needs, resulting in superior generation performance compared to vanilla RACG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19033 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation Dong, Qian Chen, Jia Ai, Qingyao Wang, Hongning Li, Haitao Wu, Yi Hu, Yao Liu, Yiqun Ma, Shaoping Information Retrieval Existing retrieval-augmented code generation (RACG) methods typically use an external retrieval module to fetch semantically similar code snippets used for generating subsequent fragments. However, even for consecutive code fragments, the content often diverges due to logical progression, resulting in a content gap. This gap undermines the performance of current RACG methods, as \textit{external} retrieval modules based on content matching fail to infer the specific information need of LLMs to generate the next code fragment. Therefore, we propose \textbf{SelfRACG}, a novel paradigm that enables large language models (LLMs) to \textbf{Self}-express their information needs to enhance \textbf{RACG}. Specifically, SelfRACG includes an information need expression module and a two-stage information need-guided training strategy, which encourages LLMs to express their information need. Extensive experiments demonstrate that SelfRACG can retrieve external knowledge that better aligns with the LLM's own information needs, resulting in superior generation performance compared to vanilla RACG. |
| title | SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2507.19033 |