mlsanityData to 7 Oct 2026

GrACE: Generation using Associated Code Edits

arXiv 2305.14129 ↗First posted 23 May 2023cs.SE cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Developers expend a significant amount of time in editing code for a variety of reasons such as bug fixing or adding new features. Designing effective methods to predict code edits has been an active yet challenging area of research due to the diversity of code edits and the difficulty of capturing the developer intent. In this work, we address these challenges by endowing pre-trained large language models (LLMs) of code with the knowledge of prior, relevant edits. The generative capability of the LLMs helps address the diversity in code changes and conditioning code generation on prior edits helps capture the latent developer intent. We evaluate two well-known LLMs, Codex and CodeT5, in zero-shot and fine-tuning settings respectively. In our experiments with two datasets, the knowledge of prior edits boosts the performance of the LLMs significantly and enables them to generate 29% and 54% more correctly edited code in top-1 suggestions relative to the current state-of-the-art symbolic and neural approaches, respectively.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 33 of its 73 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

33 of 73 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  6. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  7. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
  8. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  9. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  10. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
  11. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 600
  12. 2021Unified Pre-training for Program Understanding and Generationcited by 361
21 more
  1. 2022CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learningcited by 342
  2. 2020Unsupervised Translation of Programming Languagescited by 262
  3. 2018code2vec: Learning Distributed Representations of Codecited by 249
  4. 2018SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repaircited by 144
  5. 2020Deep Learning based Vulnerability Detection: Are We There Yet?cited by 142
  6. 2020A Transformer-based Approach for Source Code Summarizationcited by 129
  7. 2018The Adverse Effects of Code Duplication in Machine Learning Models of Codecited by 123
  8. 2019On Learning Meaningful Code Changes via Neural Machine Translationcited by 50
  9. 2019When Deep Learning Met Code Searchcited by 45
  10. 2022CoditT5: Pretraining for Source Code and Natural Language Editingcited by 45
  11. 2018CODIT: Code Editing with Tree-Based Neural Modelscited by 40
  12. 2019Getafix: Learning to Fix Bugs Automaticallycited by 40
  13. 2018Learning to Represent Editscited by 34
  14. 2022Learning to Model Editing Processescited by 30
  15. 2021On Multi-Modal Learning of Editing Source Codecited by 25
  16. 2021Leveraging the Inductive Bias of Large Language Models for Abstract Textual Reasoningcited by 18
  17. 2016Learning Syntactic Program Transformations from Examplescited by 17
  18. 2021Towards Learning (Dis)-Similarity of Source Code from Program Contrastscited by 17
  19. 2022Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languagescited by 12
  20. 2018Learning Quick Fixes from Code Repositoriescited by 8
  21. 2022Overwatch: Learning Patterns in Code Edit Sequencescited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 7; 2025: 6; 2026: 2.

16 papers.

Sort:

By area:

  1. 2024Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-stepcited by 123
  2. 2023Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructionscited by 46
  3. 2024You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projectscited by 45
  4. 2024REPOFUSE: Repository-Level Code Completion with Fused Dual Contextcited by 32
  5. 2024Towards Neural Synthesis for SMT-Assisted Proof-Oriented Programmingcited by 19
  6. 2024LLMs with Industrial Lens: Deciphering the Challenges and Prospects -- A Surveycited by 12
  7. 2026AgentStepper: Interactive Debugging of Software Development Agentscited by 8
  8. 2025Generative AI for Self-Adaptive Systems: State of the Art and Research Roadmapcited by 5
  9. 2024Can Language Models Pretend Solvers? Logic Code Simulation with LLMscited by 4
  10. 2025EditLord: Learning Code Transformation Rules for Code Editingcited by 4
  11. 2025kAgent: An execution-guided crash resolution agent for the Linux kernelcited by 4
  12. 2024No Size Fits All: The Perils and Pitfalls of Leveraging LLMs Vary with Company Sizecited by 3
4 more
  1. 2025Treefix: Enabling Execution with a Tree of Prefixescited by 2
  2. 2025NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectoriescited by 2
  3. 2026Learning from 53.6K Real-World Developer Edits of AI-Generated Codecited by 1
  4. 2025Wired for Reuse: Automating Context-Aware Code Adaptation in IDEs via LLM-Based Agentcited by 0