CodeRetriever: A Large Scale Contrastive Pre-Training Method for Code Search

By Xiaonan Li, Yeyun Gong, Yelong Shen, Xi-Peng Qiu, Bolun Yao, Weizhen Qi, Daxin Jiang, Weizhu Chen, Nan Duan. 2022

Subfields: Information Retrieval & Search, Representation & Self-Supervised Learning, Software Engineering

Citations in the corpus

• CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking (2024, unknown): “Code embedding models (Li et al., 2022a; Wang et al., 2023b; Zhang et al., 2024) have gained traction for their ability to encode the semantic and syntactic properties of code into dense vector representations and help retrieve relevant snippets with high precision.”
• Improving Code Localization with Repository Memory (2025, unknown): “Recent advances have focused on improving the quality of code embeddings, often through contrastive learning objectives (Li et al., 2022; Wang et al., 2023; Zhang et al., 2024a; Suresh et al., 2025).”