mlsanityData to 7 Oct 2026

Compilable Neural Code Generation with Compiler Feedback

arXiv 2203.05132 ↗First posted 10 Mar 2022cs.CL cs.AI cs.PLcited by 46

Not on the map. Why?

Abstract (arXiv)

Automatically generating compilable programs with (or without) natural language descriptions has always been a touchstone problem for computational linguistics and automated software engineering. Existing deep-learning approaches model code generation as text generation, either constrained by grammar structures in decoder, or driven by pre-trained language models on large-scale code corpus (e.g., CodeGPT, PLBART, and CodeT5). However, few of them account for compilability of the generated programs. To improve compilability of the generated programs, this paper proposes COMPCODER, a three-stage pipeline utilizing compiler feedback for compilable code generation, including language model fine-tuning, compilability reinforcement, and compilability discrimination. Comprehensive experiments on two code generation tasks demonstrate the effectiveness of our proposed approach, improving the success rate of compilation from 44.18 to 89.18 in code completion on average and from 70.3 to 96.2 in text-to-code generation, respectively, when comparing with the state-of-the-art CodeGPT.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Builds on 33 of its 43 references that are in the map. First posted on arXiv 10 Mar 2022.

Builds on

33 of 43 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2017Proximal Policy Optimization Algorithmscited by 14,441
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  7. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  8. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  9. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  10. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 732
  11. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
  12. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
21 more
  1. 2021Unified Pre-training for Program Understanding and Generationcited by 361
  2. 2020IntelliCode Compose: Code Generation Using Transformercited by 225
  3. 2019SPoC: Search-based Pseudocode to Codecited by 176
  4. 2018Fast Abstractive Summarization with Reinforce-Selected Sentence Rewritingcited by 158
  5. 2021Retrieval Augmented Code Generation and Summarizationcited by 148
  6. 2018SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repaircited by 144
  7. 2018Improving Automatic Source Code Summarization via Deep Reinforcement Learningcited by 99
  8. 2018Tree-to-tree Neural Networks for Program Translationcited by 93
  9. 2020Graph-based, Self-Supervised Program Repair from Diagnostic Feedbackcited by 93
  10. 2017Abstract Syntax Networks for Code Generation and Semantic Parsingcited by 92
  11. 2018A Retrieve-and-Edit Framework for Predicting Structured Outputscited by 73
  12. 2021Break-It-Fix-It: Unsupervised Learning for Program Repaircited by 71
  13. 2020Code Prediction by Feeding Trees to Transformerscited by 70
  14. 2021SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representationcited by 63
  15. 2019Code Generation as a Dual Task of Code Summarizationcited by 62
  16. 2020Multi-task Learning based Pre-trained Language Model for Code Completioncited by 58
  17. 2017Code Completion with Neural Attention and Pointer Networkscited by 49
  18. 2019Learning to Infer Program Sketchescited by 44
  19. 2019CoaCor: Code Annotation for Code Retrieval with Reinforcement Learningcited by 22
  20. 2019A Self-Attentional Neural Architecture for Code Completion with Multi-Task Learningcited by 18
  21. 2021Energy-Based Models for Code Generation under Compilability Constraintscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 13; 2024: 12; 2025: 15; 2026: 4.

46 papers.

Sort:

By area:

  1. 2024A Survey on Large Language Models for Code Generationcited by 646
  2. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 229
  3. 2023Execution-based Code Generation using Deep Reinforcement Learningcited by 95
  4. 2024If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agentscited by 77
  5. 2024StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedbackcited by 74
  6. 2023Large Language Models for Supply Chain Optimizationcited by 61
  7. 2024Agents in Software Engineering: Survey, Landscape, and Visioncited by 60
  8. 2023A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verificationcited by 42
  9. 2024Test-Driven Development for Code Generationcited by 32
  10. 2023Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attackscited by 29
  11. 2023CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Executioncited by 21
  12. 2025Process-Supervised Reinforcement Learning for Code Generationcited by 21
34 more
  1. 2023INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repaircited by 18
  2. 2025An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunitiescited by 17
  3. 2023Exploring the Robustness of Large Language Models for Solving Programming Problemscited by 16
  4. 2023B-Coder: Value-Based Deep Reinforcement Learning for Program Synthesiscited by 16
  5. 2024Code-Optimise: Self-Generated Preference Data for Correctness and Efficiencycited by 16
  6. 2022CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Trainingcited by 15
  7. 2025Pre-Trained Policy Discriminators are General Reward Modelscited by 14
  8. 2024RLSF: Fine-tuning LLMs via Symbolic Feedbackcited by 13
  9. 2023Zero-shot Visual Question Answering with Language Model Feedbackcited by 11
  10. 2023Reinforcement Learning for Generative AI: A Surveycited by 11
  11. 2025Exploring Code Language Models for Automated HLS-based Hardware Generation: Benchmark, Infrastructure and Analysiscited by 10
  12. 2025Towards an Understanding of Context Utilization in Code Intelligencecited by 10
  13. 2024Does Your Neural Code Completion Model Use My Code? A Membership Inference Approachcited by 9
  14. 2024FALCON: Feedback-driven Adaptive Long/short-term memory reinforced Coding Optimization systemcited by 8
  15. 2022CodePAD: Sequence-based Code Generation with Pushdown Automatoncited by 7
  16. 2024mathbbUSCD: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decodingcited by 6
  17. 2025Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Developmentcited by 5
  18. 2023Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code Synthesiscited by 4
  19. 2025CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedbackcited by 4
  20. 2023Neural Machine Translation for Code Generationcited by 3
  21. 2024Teaching Machines to Code: Smart Contract Translation with LLMscited by 3
  22. 2024Mastering the Craft of Data Synthesis for CodeLLMscited by 3
  23. 2025PAT-Agent: Autoformalization for Model Checkingcited by 3
  24. 2025Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLMscited by 2
  25. 2025CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchaincited by 2
  26. 2025CRPE: Expanding The Reasoning Capability of Large Language Model for Code Generationcited by 2
  27. 2025SLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learningcited by 2
  28. 2025Enhancing the Non-Functional Quality Compliance of LLM-Generated Code through Quality-Aware Preference Learningcited by 1
  29. 2025Imitation Game: Reproducing Deep Learning Bugs Leveraging an Intelligent Agentcited by 1
  30. 2026Unseen-Codebases-Domain Data Synthesis and Training Based on Code Graphscited by 1
  31. 2025BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practicecited by 0
  32. 2026EffiPair: Improving the Efficiency of LLM-generated Code with Differential Execution Feedbackcited by 0
  33. 2026Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Codecited by 0
  34. 2026Natural-Language to SysMLv2 Translation via Conformance-Driven Iterative Refinementcited by 0