mlsanityData to 14 Oct 2026

Using Pre-Trained Models to Boost Code Review Automation

arXiv 2201.06850 ↗First posted 18 Jan 2022cs.SEcited by 63

Not on the map. Why?

Abstract (arXiv)

Code review is a practice widely adopted in open source and industrial projects. Given the non-negligible cost of such a process, researchers started investigating the possibility of automating specific code review tasks. We recently proposed Deep Learning (DL) models targeting the automation of two tasks: the first model takes as input a code submitted for review and implements in it changes likely to be recommended by a reviewer; the second takes as input the submitted code and a reviewer comment posted in natural language and automatically implements the change required by the reviewer. While the preliminary results we achieved are encouraging, both models had been tested in rather simple code review scenarios, substantially simplifying the targeted problem. This was also due to the choices we made when designing both the technique and the experiments. In this paper, we build on top of that work by demonstrating that a pre-trained Text-To-Text Transfer Transformer (T5) model can outperform previous DL models for automating code review tasks. Also, we conducted our experiments on a larger and more realistic (and challenging) dataset of code review activities.

Key facts. Cited by 63 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Jan 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 10; 2024: 10; 2025: 21; 2026: 18.

63 papers.

Sort:

By area:

  1. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 399
  2. 2022Automating Code Review Activities by Large-Scale Pre-trainingcited by 98
  3. 2023LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuningcited by 47
  4. 2022CoditT5: Pretraining for Source Code and Natural Language Editingcited by 45
  5. 2023CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generationcited by 39
  6. 2024Automatic Programming: Large Language Models and Beyondcited by 36
  7. 2024CodeAgent: Autonomous Communicative Agents for Code Reviewcited by 34
  8. 20245%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Taskscited by 34
  9. 2023Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyondcited by 20
  10. 2023Adapter is All You Need for Tuning Visual Taskscited by 19
  11. 2024AI-Assisted Assessment of Coding Practices in Modern Code Reviewcited by 16
  12. 2023Benchmarking Causal Study to Interpret Large Language Models for Source Codecited by 14
38 more
  1. 2025Migrating Code At Scale With LLMs At Googlecited by 14
  2. 2022CodeEditor: Learning to Edit Source Code with Pre-trained Modelscited by 12
  3. 2023ChatGPT: A Study on its Utility for Ubiquitous Software Engineering Taskscited by 12
  4. 2024Software Vulnerability and Functionality Assessment using LLMscited by 11
  5. 2023Multilingual Code Co-Evolution Using Large Language Modelscited by 9
  6. 2023Automating Code-Related Tasks Through Transformers: The Impact of Pre-trainingcited by 8
  7. 2024CRScore: Grounding Automated Evaluation of Code Review Comments in Code Claims and Smellscited by 8
  8. 2025LAURA: Enhancing Code Review Generation with Context-Enriched Retrieval-Augmented LLMcited by 8
  9. 2024Automated User Story Generation with Test Case Specification Using Large Language Modelcited by 7
  10. 2024Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generationcited by 7
  11. 2025Evaluating Large Language Models for Code Reviewcited by 7
  12. 2022CommitBART: A Large Pre-trained Model for GitHub Commitscited by 6
  13. 2025Combining Large Language Models with Static Analyzers for Code Review Generationcited by 6
  14. 2025Retrieval-Augmented Code Review Comment Generationcited by 6
  15. 2026RovoDev Code Reviewer: A Large-Scale Online Evaluation of LLM-based Code Review Automation at Atlassiancited by 6
  16. 2025SecureReviewer: Enhancing Large Language Models for Secure Code Review through Secure-aware Fine-tuningcited by 5
  17. 2026HalluJudge: A Reference-Free Hallucination Detection for Context Misalignment in Code Review Automationcited by 5
  18. 2026Understanding Dominant Themes in Reviewing Agentic AI-authored Codecited by 5
  19. 2026AACR-Bench: Evaluating Automatic Code Review with Holistic Repository-Level Contextcited by 5
  20. 2024Leveraging Reviewer Experience in Code Review Comment Generationcited by 4
  21. 2025Evaluating the Effectiveness of LLMs in Fixing Maintainability Issues in Real-World Projectscited by 4
  22. 2025Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Modelscited by 4
  23. 2025Issue-Oriented Agent-Based Framework for Automated Review Comment Generationcited by 4
  24. 2025CodeReviewQA: The Code Review Comprehension Assessment for Large Language Modelscited by 3
  25. 2025Towards Practical Defect-Focused Automated Code Reviewcited by 3
  26. 2025DeputyDev -- AI Powered Developer Assistant: Breaking the Code Review Logjam through Contextual AI to Boost Developer Productivitycited by 3
  27. 2026Sphinx: Benchmarking and Modeling for LLM-Driven Pull Request Reviewcited by 3
  28. 2026CR-Bench: Evaluating the Real-World Utility of AI Code Review Agentscited by 3
  29. 2026Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Reviewcited by 3
  30. 2026The End of Code Review: Coding Agents Supersede Human Inspectioncited by 3
  31. 2025Improving Retrieval-Augmented Deep Assertion Generation via Joint Trainingcited by 2
  32. 2025When More Retrieval Hurts: Retrieval-Augmented Code Review Generationcited by 2
  33. 2026SWE-PRBench: Benchmarking AI Code Review Quality Against Pull Request Feedbackcited by 2
  34. 2023Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We?cited by 1
  35. 2024The Rise and Fall(?) of Software Engineeringcited by 1
  36. 2025SnipGen: A Mining Repository Framework for Evaluating LLMs for Codecited by 1
  37. 2025Leveraging Reward Models for Guiding Code Review Comment Generationcited by 1
  38. 2025Previously on... Automating Code Reviewcited by 1

50 most cited of 63 All 63 (JSON)