CoRet: Improved Retriever for Code Editing
Fabio James Fehr, Prabhu Teja S, Luca Franceschi, Giovanni Zappella
Abstract
In this paper, we introduce CoRet, a dense retrieval model designed for code-editing tasks that integrates code semantics, repository structure, and call-graph dependencies. The model focuses on retrieving relevant portions of a code repository based on natural language queries such as requests to implement new features or fix bugs. These retrieved code chunks can then be presented to an user or to a second code-editing model or agent. To train CoRet, we propose a loss function explicitly designed for repository-level retrieval. On SWE-bench and Long Code Arena’s bug localisation datasets, we show that our model substantially improves retrieval recall by at least 15 percentage points over existing models, and ablate the design choices to show their importance in achieving these results.
BibTeX
@inproceedings{fehr-etal-2025-coret,
title = "{C}o{R}et: Improved Retriever for Code Editing",
author = "Fehr, Fabio James and
Teja S, Prabhu and
Franceschi, Luca and
Zappella, Giovanni",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-short.62/",
doi = "10.18653/v1/2025.acl-short.62",
pages = "775--789",
ISBN = "979-8-89176-252-7"
}