Data to 7 Oct 2026

IntelliCode Compose: Code Generation Using Transformer

arXiv 2005.08025 ↗First posted 16 May 2020cs.CL cs.SEcited by 225

Not on the map. Why?

Abstract (arXiv)

In software development through integrated development environments (IDEs), code completion is one of the most widely used features. Nevertheless, majority of integrated development environments only support completion of methods and APIs, or arguments. In this paper, we introduce IntelliCode Compose - a general-purpose multilingual code completion tool which is capable of predicting sequences of code tokens of arbitrary types, generating up to entire lines of syntactically correct code. It leverages state-of-the-art generative transformer model trained on 1.2 billion lines of source code in Python, C#, JavaScript and TypeScript programming languages. IntelliCode Compose is deployed as a cloud-based web service. It makes use of client-side tree-based caching, efficient parallel implementation of the beam search decoder, and compute graph optimizations to meet edit-time completion suggestion requirements in the Visual Studio Code IDE and Azure Notebook. Our best model yields an average edit similarity of 86.7% and a perplexity of 1.82 for Python programming language.

Key facts. Cited by 225 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 29; 2022: 46; 2023: 57; 2024: 46; 2025: 29; 2026: 18.

225 papers.

Sort:

By area:

2021Program Synthesis with Large Language Modelscited by 3,509
2022Competition-Level Code Generation with AlphaCodecited by 1,427
2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,378
2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 732
2024A Survey on Large Language Models for Code Generationcited by 646
2023RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generationcited by 357
2022UniXcoder: Unified Cross-Modal Pre-training for Code Representationcited by 355
2023RepoBench: Benchmarking Repository-Level Code Auto-Completion Systemscited by 346
2022CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learningcited by 342
2023CodeT5+: Open Code Large Language Models for Code Understanding and Generationcited by 327
2023CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-Xcited by 294

38 more

2023An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generationcited by 193
2022Large Language Models Meet NL2Code: A Surveycited by 135
2022ReACC: A Retrieval-Augmented Code Completion Frameworkcited by 117
2023LongCoder: A Long-Range Pre-trained Language Model for Code Completioncited by 110
2022Automating Code Review Activities by Large-Scale Pre-trainingcited by 98
2022Productivity Assessment of Neural Code Completioncited by 97
2023Execution-based Code Generation using Deep Reinforcement Learningcited by 95
2024StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedbackcited by 74
2023Is ChatGPT the Ultimate Programming Assistant -- How far is it?cited by 72
2021SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representationcited by 63
2024Generating CAD Code with Vision-Language Models for 3D Designscited by 61
2024Agents in Software Engineering: Survey, Landscape, and Visioncited by 60
2024Repoformer: Selective Retrieval for Repository-Level Code Completioncited by 55
2024What's Wrong with Your Code Generated by Large Language Models? An Extensive Studycited by 52
2022CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequencescited by 49
2022Compilable Neural Code Generation with Compiler Feedbackcited by 46
2023Large Language Model-Aware In-Context Learning for Code Generationcited by 42
2021SpreadsheetCoder: Formula Prediction from Semi-structured Contextcited by 41
2022No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligencecited by 41
2023RepoFusion: Training Code Models to Understand Your Repositorycited by 40
2022Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Surveycited by 38
2024Language Models for Code Completion: A Practical Evaluationcited by 38
2021What do pre-trained code models know about code?cited by 36
2025LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarkscited by 34
2023Code Execution with Pre-trained Language Modelscited by 33
2025Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Supportcited by 33
2023Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Reviewcited by 32
2024An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detectioncited by 32
2022Training and Evaluating a Jupyter Notebook Data Science Assistantcited by 31
2023Learning Deep Semantics for Test Completioncited by 31
2023DeceptPrompt: Exploiting LLM-driven Code Generation via Adversarial Natural Language Instructionscited by 31
2021Code Completion by Modeling Flattened Abstract Syntax Trees as Graphscited by 30
2022On the Transferability of Pre-trained Language Models for Low-Resource Programming Languagescited by 30
2023Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attackscited by 29
2023Large Language Models of Code Fail at Completing Code with Potential Bugscited by 28
2023Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generationcited by 27
2023Refactoring Programs Using Large Language Models with Few-Shot Examplescited by 27
2021How could Neural Networks understand Programs?cited by 26

50 most cited of 225 All 225 (JSON)