mlsanityData to 7 Oct 2026

CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context

arXiv 2212.10007 ↗First posted 20 Dec 2022cs.CL cs.SEcited by 64

Not on the map. Why?

Abstract (arXiv)

While pre-trained language models (LM) for code have achieved great success in code completion, they generate code conditioned only on the contents within the file, i.e., in-file context, but ignore the rich semantics in other files within the same project, i.e., cross-file context, a critical source of information that is especially useful in modern modular software development. Such overlooking constrains code language models' capacity in code completion, leading to unexpected behaviors such as generating hallucinated class member functions or function calls with unexpected arguments. In this work, we develop a cross-file context finder tool, CCFINDER, that effectively locates and retrieves the most relevant cross-file context. We propose CoCoMIC, a framework that incorporates cross-file context to learn the in-file and cross-file context jointly on top of pretrained code LMs. CoCoMIC successfully improves the existing code LM with a 33.94% relative increase in exact match and a 28.69% relative increase in identifier matching for code completion when the cross-file context is provided.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). Builds on 29 of its 61 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

29 of 61 references.

References · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2017Graph Attention Networkscited by 8,854
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2021Program Synthesis with Large Language Modelscited by 3,509
  5. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  6. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
  7. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  8. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  9. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
  10. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  11. 2022GPT-NeoX-20B: An Open-Source Autoregressive Language Modelcited by 711
  12. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
17 more
  1. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 600
  2. 2019Quantifying the Carbon Emissions of Machine Learningcited by 516
  3. 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 492
  4. 2021Unified Pre-training for Program Understanding and Generationcited by 361
  5. 2022A Systematic Evaluation of Large Language Models of Codecited by 360
  6. 2022UniXcoder: Unified Cross-Modal Pre-training for Code Representationcited by 355
  7. 2019Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networkscited by 266
  8. 2022Grounded Copilot: How Programmers Interact with Code-Generating Modelscited by 216
  9. 2022DocPrompting: Generating Code by Retrieving the Docscited by 151
  10. 2018An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translationcited by 106
  11. 2022Repository-Level Prompt Generation for Large Language Models of Codecited by 106
  12. 2020Improved Automatic Summarization of Subroutines via Attention to File Contextcited by 34
  13. 2021GNN-LM: Language Modeling based on Global Contexts via GNNcited by 27
  14. 2021CoCoSum: Contextual Code Summarization with Multi-Relational Graph Neural Networkcited by 22
  15. 2020A Toolkit for Generating Code Knowledge Graphscited by 17
  16. 2021Towards Learning (Dis)-Similarity of Source Code from Program Contrastscited by 17
  17. 2021Can Machines Read Coding Manuals Yet? -- A Benchmark for Building Better Language Models for Code Understandingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 12; 2024: 27; 2025: 16; 2026: 9.

64 papers.

Sort:

By area:

  1. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  2. 2024A Survey on Large Language Models for Code Generationcited by 646
  3. 2023LeanDojo: Theorem Proving with Retrieval-Augmented Language Modelscited by 414
  4. 2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 357
  5. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  6. 2023RepoBench: Benchmarking Repository-Level Code Auto-Completion Systemscited by 346
  7. 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Executioncited by 294
  8. 2023CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completioncited by 181
  9. 2023OctoPack: Instruction Tuning Code Large Language Modelscited by 178
  10. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 84
  11. 2025SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agentscited by 80
  12. 2023Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Codecited by 62
38 more
  1. 2024EffiBench: Benchmarking the Efficiency of Automatically Generated Codecited by 62
  2. 2024Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Explorationcited by 58
  3. 2024Repoformer: Selective Retrieval for Repository-Level Code Completioncited by 55
  4. 2023Bias Testing and Mitigation in LLM-based Code Generationcited by 53
  5. 2024Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedbackcited by 45
  6. 2024You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projectscited by 45
  7. 2023RepoFusion: Training Code Models to Understand Your Repositorycited by 40
  8. 2024Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completioncited by 40
  9. 2024GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Modelcited by 40
  10. 2024SWE-bench-java: A GitHub Issue Resolving Benchmark for Javacited by 34
  11. 2024REPOFUSE: Repository-Level Code Completion with Fused Dual Contextcited by 32
  12. 2025Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Taskscited by 27
  13. 2024MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generationcited by 25
  14. 2024Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Taskscited by 24
  15. 2025What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyondcited by 22
  16. 2024On the Impacts of Contexts on Repository-Level Code Generationcited by 21
  17. 2024M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluationcited by 21
  18. 2023Guiding Language Models of Code with Global Context using Monitorscited by 20
  19. 2025Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approachescited by 20
  20. 2024ExecRepoBench: Multi-level Executable Code Completion Evaluationcited by 19
  21. 2024Prompt-based Code Completion via Multi-Retrieval Augmented Generationcited by 16
  22. 2024RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completioncited by 15
  23. 2024Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmarkcited by 13
  24. 2025CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completioncited by 12
  25. 2024Enhancing LLM-Based Coding Tools through Native Integration of IDE-Derived Static Contextcited by 10
  26. 2024RAMBO: Enhancing RAG-based Repository-Level Method Body Completioncited by 10
  27. 2025Towards an Understanding of Context Utilization in Code Intelligencecited by 10
  28. 2024R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Modelscited by 9
  29. 2024Statically Contextualizing Large Language Models with Typed Holescited by 9
  30. 2025RANGER -- Repository-Level Agent for Graph-Enhanced Retrievalcited by 7
  31. 2026AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completioncited by 7
  32. 2025Knowledge Augmented Complex Problem Solving with Large Language Models: A Surveycited by 6
  33. 2025Enhancing Project-Specific Code Completion by Inferring Internal API Informationcited by 5
  34. 2025Impact-driven Context Filtering For Cross-file Code Completioncited by 5
  35. 2023Revisiting File Context for Source Code Summarizationcited by 3
  36. 2025CoRet: Improved Retriever for Code Editingcited by 3
  37. 2026RepoShapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completioncited by 3
  38. 2026DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoningcited by 3

50 most cited of 64 All 64 (JSON)