RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry

Documenti analoghi

• A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat
  di: Yang, Zezhou, et al.
  Pubblicazione: (2025)
• Cascaded Code Editing: Large-Small Model Collaboration for Effective and Efficient Code Editing
  di: Wang, Chaozheng, et al.
  Pubblicazione: (2026)
• SEER: Enhancing Chain-of-Thought Code Generation through Self-Exploring Deep Reasoning
  di: Gao, Shuzheng, et al.
  Pubblicazione: (2025)
• Exploring Multi-Lingual Bias of Large Code Models in Code Generation
  di: Wang, Chaozheng, et al.
  Pubblicazione: (2024)
• Automated Prompt Generation for Code Intelligence: An Empirical study and Experience in WeChat
  di: Ji, Kexing, et al.
  Pubblicazione: (2025)