mlsanityData to 7 Oct 2026

Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion

arXiv 2405.19782 ↗First posted 30 May 2024cs.SE cs.CLcited by 40

Not on the map. Why?

Abstract (arXiv)

Recent years have witnessed the deployment of code language models (LMs) in various code intelligence tasks such as code completion. Yet, it is challenging for pre-trained LMs to generate correct completions in private repositories. Previous studies retrieve cross-file context based on import relations or text similarity, which is insufficiently relevant to completion targets. In this paper, we propose a dataflow-guided retrieval augmentation approach, called DraCo, for repository-level code completion. DraCo parses a private repository into code entities and establishes their relations through an extended dataflow analysis, forming a repo-specific context graph. Whenever triggering code completion, DraCo precisely retrieves relevant background knowledge from the repo-specific context graph and generates well-formed prompts to query code LMs. Furthermore, we construct a large Python dataset, ReccEval, with more diverse completion targets. Our experiments demonstrate the superior accuracy and applicable efficiency of DraCo, improving code exact match by 3.43% and identifier F1-score by 3.27% on average compared to the state-of-the-art approach.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 44 of its 67 references that are in the map. First posted on arXiv 30 May 2024.

Builds on

44 of 67 references.

References · 44

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  7. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  8. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  9. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  10. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  11. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  12. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
32 more
  1. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  2. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 732
  3. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  4. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
  5. 2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 357
  6. 2023RepoBench: Benchmarking Repository-Level Code Auto-Completion Systemscited by 346
  7. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  8. 2023CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-Xcited by 294
  9. 2022Grounded Copilot: How Programmers Interact with Code-Generating Modelscited by 216
  10. 2023CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completioncited by 181
  11. 2022GitHub Copilot AI pair programmer: Asset or Liability?cited by 150
  12. 2021Retrieval Augmented Code Generation and Summarizationcited by 148
  13. 2022ReACC: A Retrieval-Augmented Code Completion Frameworkcited by 117
  14. 2022Repository-Level Prompt Generation for Large Language Models of Codecited by 106
  15. 2023WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferencescited by 100
  16. 2020Retrieval-Augmented Generation for Code Summarization via Hybrid GNNcited by 89
  17. 2023Studying the effect of AI Code Generators on Supporting Novice Learners in Introductory Programmingcited by 87
  18. 2018A Retrieve-and-Edit Framework for Predicting Structured Outputscited by 73
  19. 2024EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositoriescited by 71
  20. 2020Code Prediction by Feeding Trees to Transformerscited by 70
  21. 2023PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedbackcited by 69
  22. 2022CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Contextcited by 64
  23. 2019Pythia: AI-assisted Code Completion Systemcited by 54
  24. 2017Code Completion with Neural Attention and Pointer Networkscited by 49
  25. 2022CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequencescited by 49
  26. 2023Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applicationscited by 28
  27. 2023AceCoder: Utilizing Existing Code to Enhance Code Generationcited by 25
  28. 2021Revisiting, Benchmarking and Exploring API Recommendation: How Far Are We?cited by 21
  29. 2023Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completioncited by 14
  30. 2021Static Inference Meets Deep Learning: A Hybrid Type Inference Approach for Pythoncited by 12
  31. 2023Automating Code-Related Tasks Through Transformers: The Impact of Pre-trainingcited by 8
  32. 2021PyART: Python API Recommendation in Real-Timecited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 18; 2026: 18.

40 papers.

Sort:

By area:

  1. 2024RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graphcited by 88
  2. 2024CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databasescited by 62
  3. 2025Knowledge Graph-Guided Retrieval Augmented Generationcited by 57
  4. 2025What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyondcited by 22
  5. 2025Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approachescited by 20
  6. 2026In Line with Context: Repository-Level Code Generation via Context Inliningcited by 18
  7. 2025CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completioncited by 12
  8. 2024JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Modelscited by 10
  9. 2025Towards an Understanding of Context Utilization in Code Intelligencecited by 10
  10. 2025Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspectivecited by 8
  11. 2026SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Executioncited by 8
  12. 2025RANGER -- Repository-Level Agent for Graph-Enhanced Retrievalcited by 7
28 more
  1. 2026AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completioncited by 7
  2. 2025A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChatcited by 5
  3. 2025Impact-driven Context Filtering For Cross-file Code Completioncited by 5
  4. 2025Detection of LLM-Paraphrased Code and Identification of the Responsible LLM Using Coding Style Featurescited by 4
  5. 2025RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Modelscited by 4
  6. 2025CodeSSM: Towards State Space Models for Code Understandingcited by 3
  7. 2025Practical Code RAG at Scale: Task-Aware Retrieval Design Choices under Compute Budgetscited by 3
  8. 2026RepoShapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completioncited by 3
  9. 2026Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answeringcited by 3
  10. 2025FastCoder: Accelerating Repository-level Code Generation via Efficient Retrieval and Verificationcited by 2
  11. 2025TENET: One Step Toward Test-Driven Development for Repository-Level Code Generationcited by 2
  12. 2026Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Modelscited by 2
  13. 2025CRABS: A syntactic-semantic pincer strategy for bounding LLM interpretation of Python notebookscited by 1
  14. 2025LSPRAG: LSP-Guided RAG for Language-Agnostic Real-Time Unit Test Generationcited by 1
  15. 2026Bridging the Knowledge Void: Inference-time Acquisition of Unfamiliar Programming Languages for Coding Taskscited by 1
  16. 2026MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answeringcited by 1
  17. 2026ReCUBE: Evaluating Repository-Level Context Utilization in Code Generationcited by 1
  18. 2026ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarizationcited by 1
  19. 2026Effective and Efficient Context Retrieval via Partial Dependency Graph for Repository-Level Code Generationcited by 1
  20. 2026ReproAgent: Contract-Guided Paper-to-Code Reproductioncited by 1
  21. 2024A Lightweight Framework for Adaptive Retrieval In Code Completion With Critique Modelcited by 0
  22. 2025SaraCoder: Orchestrating Semantic and Structural Cues for Resource-Optimized Repository-Level Code Completioncited by 0
  23. 2026Automated Customization of LLMs for Enterprise Code Repositories Using Semantic Scopescited by 0
  24. 2026Hierarchical Embedding Fusion for Retrieval-Augmented Code Generationcited by 0
  25. 2026How Does Chunking Affect Retrieval-Augmented Code Completion? A Controlled Empirical Studycited by 0
  26. 2026Dependency-Guided Code Generation: Structured Matrix Decomposition and Consistency-Guided Refinementcited by 0
  27. 2026Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generationcited by 0
  28. 2026FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generationcited by 0