mlsanityData to 7 Oct 2026

Repair Is Nearly Generation: Multilingual Program Repair with LLMs

arXiv 2208.11640 ↗First posted 24 Aug 2022cs.SE cs.AI cs.PLcited by 68

Not on the map. Why?

Abstract (arXiv)

Most programmers make mistakes when writing code. Some of these mistakes are small and require few edits to the original program -- a class of errors recently termed last mile mistakes. These errors break the flow for experienced developers and can stump novice programmers. Existing automated repair techniques targeting this class of errors are language-specific and do not easily carry over to new languages. Transferring symbolic approaches requires substantial engineering and neural approaches require data and retraining. We introduce RING, a multilingual repair engine powered by a large language model trained on code (LLMC) such as Codex. Such a multilingual engine enables a flipped model for programming assistance, one where the programmer writes code and the AI assistance suggests fixes, compared to traditional code suggestion technology. Taking inspiration from the way programmers manually fix bugs, we show that a prompt-based strategy that conceptualizes repair as localization, transformation, and candidate ranking, can successfully repair programs in multiple languages with minimal effort. We present the first results for such a multilingual repair engine by evaluating on 6 different languages and comparing performance to language-specific repair engines. We show that RING can outperform language-specific repair engines for three of these languages.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). Builds on 19 of its 49 references that are in the map. First posted on arXiv 24 Aug 2022.

Builds on

19 of 49 references.

References · 19

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  5. 2017Billion-scale similarity search with GPUscited by 2,477
  6. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  7. 2019Measuring Calibration in Deep Learningcited by 443
  8. 2022Synchromesh: Reliable code generation from pre-trained language modelscited by 156
  9. 2021A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Levelcited by 96
  10. 2020Graph-based, Self-Supervised Program Repair from Diagnostic Feedbackcited by 93
  11. 2021Break-It-Fix-It: Unsupervised Learning for Program Repaircited by 71
  12. 2022Code Generation Tools (Almost) for Free? A Study of Few-Shot, Pre-Trained Language Models on Codecited by 39
7 more
  1. 2022Fault-Aware Neural Code Rankerscited by 33
  2. 2022Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuningcited by 25
  3. 2021Automatic Program Repair with OpenAI's Codex: Evaluating QuixBugscited by 24
  4. 2021Learning to Complete Code with Sketchescited by 23
  5. 2022Neurosymbolic Repair for Low-Code Formula Languagescited by 12
  6. 2016sk_p: a neural program corrector for MOOCscited by 10
  7. 2018Don't Panic! Better, Fewer, Syntax Errors for LR Parserscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 20; 2024: 23; 2025: 15; 2026: 8.

68 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  2. 2024RepairAgent: An Autonomous, LLM-Based Agent for Program Repaircited by 225
  3. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 173
  4. 2022Large Language Models Meet NL2Code: A Surveycited by 135
  5. 2024From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Futurecited by 85
  6. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 84
  7. 2023Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)cited by 72
  8. 2025FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementationcited by 57
  9. 2023Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repaircited by 55
  10. 2023RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repaircited by 50
  11. 2023Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructionscited by 46
  12. 2023Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMscited by 45
38 more
  1. 2023RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repaircited by 43
  2. 2023A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verificationcited by 42
  3. 2023Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Modelscited by 38
  4. 2023Generating High-Precision Feedback for Programming Syntax Errors using Large Language Modelscited by 34
  5. 2023Fully Autonomous Programming with Large Language Modelscited by 31
  6. 2022Repairing Bugs in Python Assignments Using Large Language Modelscited by 28
  7. 2023Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Modelscited by 28
  8. 2023Refactoring Programs Using Large Language Models with Few-Shot Examplescited by 27
  9. 2024Learning Agent-based Modeling with LLM Companions: Experiences of Novices and Experts Using ChatGPT & NetLogo Chatcited by 23
  10. 2023Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmapscited by 19
  11. 2023Exploring the Robustness of Large Language Models for Solving Programming Problemscited by 16
  12. 2023FLAME: A small language model for spreadsheet formulascited by 15
  13. 2023FRANC: A Lightweight Framework for High-Quality Code Generationcited by 14
  14. 2024Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicatescited by 14
  15. 2024Learning Task Decomposition to Assist Humans in Competitive Programmingcited by 14
  16. 2025To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Promptcited by 14
  17. 2024Aligning the Objective of LLM-based Program Repaircited by 12
  18. 2024FT2Ra: A Fine-Tuning-Inspired Approach to Retrieval-Augmented Code Completioncited by 9
  19. 2024Statically Contextualizing Large Language Models with Typed Holescited by 9
  20. 2023CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generationcited by 8
  21. 2024Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localizationcited by 8
  22. 2024DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Modelscited by 7
  23. 2024Can GPT-O1 Kill All Bugs? An Evaluation of GPT-Family LLMs on QuixBugscited by 7
  24. 2024TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignmentcited by 7
  25. 2025Large Language Model Guided Self-Debugging Code Generationcited by 7
  26. 2024A Methodology for Evaluating RAG Systems: A Case Study On Configuration Dependency Validationcited by 6
  27. 2023Frustrated with Code Quality Issues? LLMs can Help!cited by 5
  28. 2025PredicateFix: Repairing Static Analysis Alerts with Bridging Predicatescited by 5
  29. 2025Impact-driven Context Filtering For Cross-file Code Completioncited by 5
  30. 2024Aligners: Decoupling LLMs and Alignmentcited by 4
  31. 2024A Survey on Large Language Models from Concept to Implementationcited by 4
  32. 2024Enhancing Source Code Security with LLMs: Demystifying The Challenges and Generating Reliable Repairscited by 4
  33. 2025Simplifying Root Cause Analysis in Kubernetes with StateGraph and LLMcited by 4
  34. 2025PyVeritas: On Verifying Python via LLM-Based Transpilation and Bounded Model Checking for Ccited by 4
  35. 2024Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMscited by 3
  36. 2024Renaissance of Literate Programming in the Era of LLMs: Enhancing LLM-Based Code Generation in Large-Scale Projectscited by 3
  37. 2025Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinementcited by 3
  38. 2025Diffusion is a code repair operator and generatorcited by 3

50 most cited of 68 All 68 (JSON)