@inproceedings{wang-etal-2025-coderag,
title = "{C}ode{RAG}-Bench: Can Retrieval Augment Code Generation?",
author = "Wang, Zora Zhiruo and
Asai, Akari and
Yu, Xinyan Velocity and
Xu, Frank F. and
Xie, Yiqing and
Neubig, Graham and
Fried, Daniel",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.176/",
doi = "10.18653/v1/2025.findings-naacl.176",
pages = "3199--3214",
ISBN = "979-8-89176-195-7",
abstract = "While language models (LMs) excel at generating code, many programs are difficult to generate using only parametric knowledge. Despite the success of retrieval-augmented generation (RAG) in text-centric tasks, its potential for code generation remains under-explored. This work introduces CodeRAG-bench, a holistic retrieval-augmented code generation benchmark covering tasks like basic programming, open-domain, and repository-level problems and provides reproducible evaluations on both retrieval and end-to-end code generation performance. We further create a diverse, open datastore for code retrieval, aggregating sources such as competition solutions, tutorials, library documentation, StackOverflow posts, and GitHub repositories. Based on CodeRAG-bench, we conduct large-scale evaluations of 10 retrievers and 10 LMs and systematically analyze when retrieval can benefit code generation models and identify remaining challenges. We find that while retrieving high-quality contexts improves code generation, retrievers often struggle to fetch useful contexts, and generators face limitations in using those contexts effectively. We hope CodeRAG-bench encourages further development in code-oriented RAG methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-coderag">
<titleInfo>
<title>CodeRAG-Bench: Can Retrieval Augment Code Generation?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zora</namePart>
<namePart type="given">Zhiruo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akari</namePart>
<namePart type="family">Asai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyan</namePart>
<namePart type="given">Velocity</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiqing</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Fried</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>While language models (LMs) excel at generating code, many programs are difficult to generate using only parametric knowledge. Despite the success of retrieval-augmented generation (RAG) in text-centric tasks, its potential for code generation remains under-explored. This work introduces CodeRAG-bench, a holistic retrieval-augmented code generation benchmark covering tasks like basic programming, open-domain, and repository-level problems and provides reproducible evaluations on both retrieval and end-to-end code generation performance. We further create a diverse, open datastore for code retrieval, aggregating sources such as competition solutions, tutorials, library documentation, StackOverflow posts, and GitHub repositories. Based on CodeRAG-bench, we conduct large-scale evaluations of 10 retrievers and 10 LMs and systematically analyze when retrieval can benefit code generation models and identify remaining challenges. We find that while retrieving high-quality contexts improves code generation, retrievers often struggle to fetch useful contexts, and generators face limitations in using those contexts effectively. We hope CodeRAG-bench encourages further development in code-oriented RAG methods.</abstract>
<identifier type="citekey">wang-etal-2025-coderag</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.176</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.176/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>3199</start>
<end>3214</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CodeRAG-Bench: Can Retrieval Augment Code Generation?
%A Wang, Zora Zhiruo
%A Asai, Akari
%A Yu, Xinyan Velocity
%A Xu, Frank F.
%A Xie, Yiqing
%A Neubig, Graham
%A Fried, Daniel
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F wang-etal-2025-coderag
%X While language models (LMs) excel at generating code, many programs are difficult to generate using only parametric knowledge. Despite the success of retrieval-augmented generation (RAG) in text-centric tasks, its potential for code generation remains under-explored. This work introduces CodeRAG-bench, a holistic retrieval-augmented code generation benchmark covering tasks like basic programming, open-domain, and repository-level problems and provides reproducible evaluations on both retrieval and end-to-end code generation performance. We further create a diverse, open datastore for code retrieval, aggregating sources such as competition solutions, tutorials, library documentation, StackOverflow posts, and GitHub repositories. Based on CodeRAG-bench, we conduct large-scale evaluations of 10 retrievers and 10 LMs and systematically analyze when retrieval can benefit code generation models and identify remaining challenges. We find that while retrieving high-quality contexts improves code generation, retrievers often struggle to fetch useful contexts, and generators face limitations in using those contexts effectively. We hope CodeRAG-bench encourages further development in code-oriented RAG methods.
%R 10.18653/v1/2025.findings-naacl.176
%U https://aclanthology.org/2025.findings-naacl.176/
%U https://doi.org/10.18653/v1/2025.findings-naacl.176
%P 3199-3214
Markdown (Informal)
[CodeRAG-Bench: Can Retrieval Augment Code Generation?](https://aclanthology.org/2025.findings-naacl.176/) (Wang et al., Findings 2025)
ACL
- Zora Zhiruo Wang, Akari Asai, Xinyan Velocity Yu, Frank F. Xu, Yiqing Xie, Graham Neubig, and Daniel Fried. 2025. CodeRAG-Bench: Can Retrieval Augment Code Generation?. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 3199–3214, Albuquerque, New Mexico. Association for Computational Linguistics.