mlsanityData to 7 Oct 2026

Learning to Update Natural Language Comments Based on Code Changes

arXiv 2004.12169 ↗First posted 25 Apr 2020cs.CL cs.LG cs.SEcited by 30

Not on the map. Why?

Abstract (arXiv)

We formulate the novel task of automatically updating an existing natural language comment based on changes in the body of code it accompanies. We propose an approach that learns to correlate changes across two distinct language representations, to generate a sequence of edits that are applied to the existing comment to reflect the source code modifications. We train and evaluate our model using a dataset that we collected from commit histories of open-source software projects, with each example consisting of a concurrent update to a method and its corresponding comment. We compare our approach against multiple baselines using both automatic metrics and human evaluation. Results reflect the challenge of this task and that our model outperforms baselines with respect to making edits.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 6; 2023: 7; 2024: 2; 2025: 2; 2026: 4.

30 papers.

Sort:

By area:

  1. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thoughtcited by 118
  2. 2021On the Evaluation of Neural Code Summarizationcited by 47
  3. 2022CoditT5: Pretraining for Source Code and Natural Language Editingcited by 45
  4. 2021NL-EDIT: Correcting semantic parse errors through natural language interactioncited by 33
  5. 2023Learning Deep Semantics for Test Completioncited by 31
  6. 2022RACE: Retrieval-Augmented Commit Message Generationcited by 27
  7. 2023Deep Learning for Code Intelligence: Survey, Benchmark and Toolkitcited by 22
  8. 2021Learning Structural Edits via Incremental Tree Transformationscited by 16
  9. 2022Source Code Summarization with Structural Relative Position Guided Transformercited by 14
  10. 2023TypeT5: Seq2seq Type Inference using Static Analysiscited by 12
  11. 2021Impact of Evaluation Methodologies on Code Summarizationcited by 11
  12. 2023Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editingcited by 9
18 more
  1. 2023Multilingual Code Co-Evolution Using Large Language Modelscited by 9
  2. 2024Natural Language Outlines for Code: Literate Programming in the LLM Eracited by 9
  3. 2022Code Comment Inconsistency Detection with BERT and Longformercited by 6
  4. 2021Learning to Generate Code Comments from Class Hierarchiescited by 5
  5. 2021Learning to Describe Solutions for Bug Reports Based on Developer Discussionscited by 5
  6. 2026ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Filescited by 5
  7. 2024exLong: Generating Exceptional Behavior Tests with Large Language Modelscited by 4
  8. 2021ComSum: Commit Messages Summarization and Meaning Preservationcited by 3
  9. 2021GN-Transformer: Fusing Sequence and Graph Representation for Improved Code Summarizationcited by 3
  10. 2022A Survey on Natural Language Processing for Programmingcited by 3
  11. 2023CCRep: Learning Code Change Representations via Pre-Trained Code Model and Query Backcited by 3
  12. 2025TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammarcited by 2
  13. 2026Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Codingcited by 2
  14. 2021Data-Driven AI Model Signal-Awareness Enhancement and Introspectioncited by 1
  15. 2022LAMNER: Code Comment Generation Using Character Language Model and Named Entity Recognitioncited by 1
  16. 2026RefactorAssist: Agentic Refinement for Reliable Code Refactoringcited by 1
  17. 2025Excision Score: Evaluating Edits with Surgical Precisioncited by 0
  18. 2026From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentationcited by 0