Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion (2403.06095v4)

Published 10 Mar 2024 in cs.SE and cs.AI

Abstract: Code LLMs (CodeLLMs) have demonstrated impressive proficiency in code completion tasks. However, they often fall short of fully understanding the extensive context of a project repository, such as the intricacies of relevant files and class hierarchies, which can result in less precise completions. To overcome these limitations, we present \tool, a multifaceted framework designed to address the complex challenges associated with repository-level code completion. Central to RepoHYPER is the {\em Repo-level Semantic Graph} (RSG), a novel semantic graph structure that encapsulates the vast context of code repositories. Furthermore, RepoHyper leverages Expand and Refine retrieval method, including a graph expansion and a link prediction algorithm applied to the RSG, enabling the effective retrieval and prioritization of relevant code snippets. Our evaluations show that \tool markedly outperforms existing techniques in repository-level code completion, showcasing enhanced accuracy across various datasets when compared to several strong baselines. Our implementation of RepoHYPER can be found at https://github.com/FSoft-AI4Code/RepoHyper.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. Guiding language models of code with global context using monitors. arXiv preprint arXiv:2306.10763.
  2. Program synthesis with large language models. arXiv preprint arXiv:2108.07732.
  3. Codeplan: Repository-level coding using llms and planning. arXiv preprint arXiv:2309.12499.
  4. Codetf: One-stop transformer library for state-of-the-art code llm. arXiv preprint arXiv:2306.00029.
  5. Evaluating large language models trained on code.
  6. Extending context window of large language models via positional interpolation. arXiv preprint arXiv:2306.15595.
  7. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, 24(240):1–113.
  8. Tri Dao. 2023. Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691.
  9. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems, 35:16344–16359.
  10. Crosscodeeval: A diverse and multilingual benchmark for cross-file code completion. arXiv preprint arXiv:2310.11248.
  11. Cocomic: Code completion by jointly modeling in-file and cross-file context. arXiv preprint arXiv:2212.10007.
  12. Unixcoder: Unified cross-modal pre-training for code representation. arXiv preprint arXiv:2203.03850.
  13. Deepseek-coder: When the large language model meets programming – the rise of code intelligence.
  14. Inductive representation learning on large graphs. In NIPS.
  15. Measuring coding challenge competence with apps. arXiv preprint arXiv:2105.09938.
  16. Starcoder: may the source be with you!
  17. Context-aware code generation framework for code repositories: Local, global, and third-party library awareness. arXiv preprint arXiv:2312.05772.
  18. Repobench: Benchmarking repository-level code auto-completion systems.
  19. Repocoder: Repository-level code completion through cross-file context retrieval. arXiv preprint arXiv:2303.12570.
  20. Wizardcoder: Empowering code large language models with evol-instruct. arXiv preprint arXiv:2306.08568.
  21. OpenDialKG: Explainable conversational reasoning with attention-based walks over knowledge graphs. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 845–854, Florence, Italy. Association for Computational Linguistics.
  22. Codegen2: Lessons for training llms on programming and natural languages. arXiv preprint arXiv:2305.02309.
  23. Codegen: An open large language model for code with multi-turn program synthesis.
  24. Carbon emissions and large neural network training.
  25. Train short, test long: Attention with linear biases enables input length extrapolation. arXiv preprint arXiv:2108.12409.
  26. Codebleu: a method for automatic evaluation of code synthesis. arXiv preprint arXiv:2009.10297.
  27. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950.
  28. Repofusion: Training code models to understand your repository.
  29. Repository-level prompt generation for large language models of code. In ICML 2022 Workshop on Knowledge Retrieval and Language Models.
  30. Repository-level prompt generation for large language models of code. In International Conference on Machine Learning, pages 31693–31715. PMLR.
  31. CodeT5+: Open code large language models for code understanding and generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1069–1088, Singapore. Association for Computational Linguistics.
  32. Codet5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. arXiv preprint arXiv:2109.00859.
  33. Rlpg: A reinforcement learning based code completion system with graph-based context representation. In Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2021, page 1119–1129, New York, NY, USA. Association for Computing Machinery.
  34. Codeagent: Enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges. arXiv preprint arXiv:2401.07339.
  35. Codegeex: A pre-trained model for code generation with multilingual evaluations on humaneval-x.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Huy N. Phan (2 papers)
  2. Hoang N. Phan (2 papers)
  3. Tien N. Nguyen (24 papers)
  4. Nghi D. Q. Bui (30 papers)
Citations (1)
View on Semantic Scholar