CoRet: Improved Retriever for Code Editing
Not on the map. Why?
Abstract (arXiv)
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 a 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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 40 of its 57 references that are in the map. First posted on arXiv 30 May 2025.
Builds on
40 of 57 references.
References · 40
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
- 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
- 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
- 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,310
- 2021Improving language models by retrieving from trillions of tokenscited by 1,293
- 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
- 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,181
28 more
- 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
- 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
- 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 744
- 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 654
- 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 609
- 2024LLM2Vec: Large Language Models Are Secretly Powerful Text Encoderscited by 404
- 2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 367
- 2022UniXcoder: Unified Cross-Modal Pre-training for Code Representationcited by 361
- 2023Large Language Models for Information Retrieval: A Surveycited by 331
- 2020Sparse, Dense, and Attentional Representations for Text Retrievalcited by 214
- 2020Pre-training via Paraphrasingcited by 92
- 2024CodeRAG-Bench: Can Retrieval Augment Code Generation?cited by 91
- 2024RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graphcited by 91
- 2021CoSQA: 20,000+ Web Queries for Code Search and Question Answeringcited by 75
- 2024Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Modelscited by 73
- 2024SpecRover: Code Intent Extraction via LLMscited by 72
- 2022CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Contextcited by 65
- 2024CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databasescited by 65
- 2024CoIR: A Comprehensive Benchmark for Code Information Retrieval Modelscited by 60
- 2024Long Code Arena: a Set of Benchmarks for Long-Context Code Modelscited by 50
- 2024CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Rerankingcited by 37
- 2024EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluationscited by 34
- 2019Learning and Evaluating Contextual Embedding of Source Codecited by 33
- 2024LLMs are Also Effective Embedding Models: An In-depth Overviewcited by 32
- 2021Project-Level Encoding for Neural Source Code Summarization of Subroutinescited by 24
- 2013Prediction and Clustering in Signed Networks: A Local to Global Perspectivecited by 5
- 2013A Correlation Clustering Approach to Link Classification in Signed Networks -- Full Version --cited by 4
- 2017Predicting Positive and Negative Links with Noisy Queries: Theory & Practicecited by 3
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.