# EditSum: A Retrieve-and-Edit Framework for Source Code Summarization

arXiv: https://arxiv.org/abs/2308.13775 · HTML: https://mlsanity.com/paper/2308.13775/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 36 references that are in the map.
- First posted on arXiv 26 Aug 2023.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Six Challenges for Neural Machine Translation](https://mlsanity.com/paper/1706.03872/) (2017)
- [A Survey of Machine Learning for Big Code and Naturalness](https://mlsanity.com/paper/1709.06182/) (2017)
- [Generating Sentences by Editing Prototypes](https://mlsanity.com/paper/1709.08878/) (2017)
- [A Neural Model for Generating Natural Language Summaries of Program Subroutines](https://mlsanity.com/paper/1902.01954/) (2019)
- [Retrieve and Refine: Exemplar-based Neural Comment Generation](https://mlsanity.com/paper/1910.10419/) (2019)
- [Code to Comment "Translation": Data, Metrics, Baselining & Evaluation](https://mlsanity.com/paper/2010.01410/) (2020)

## Built on by (most cited first, 18 of 18)

- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair](https://mlsanity.com/paper/2309.06057/) (2023)
- [A Survey on Knowledge-Oriented Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.10677/) (2025)
- [Rango: Adaptive Retrieval-Augmented Proving for Automated Software Verification](https://mlsanity.com/paper/2412.14063/) (2024)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Tasks](https://mlsanity.com/paper/2503.12029/) (2025)
- [ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarization](https://mlsanity.com/paper/2407.01646/) (2024)
- [Retrieval-Augmented Code Review Comment Generation](https://mlsanity.com/paper/2506.11591/) (2025)
- [Revisiting and Improving Retrieval-Augmented Deep Assertion Generation](https://mlsanity.com/paper/2309.10264/) (2023)
- [Improving Retrieval-Augmented Code Comment Generation by Retrieving for Generation](https://mlsanity.com/paper/2408.03623/) (2024)
- [Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Models](https://mlsanity.com/paper/2502.16071/) (2025)
- [MESIA: Understanding and Leveraging Supplementary Nature of Method-level Comments for Automatic Comment Generation](https://mlsanity.com/paper/2403.17357/) (2024)
- [Improving Retrieval-Augmented Deep Assertion Generation via Joint Training](https://mlsanity.com/paper/2502.10696/) (2025)
- [Generating Equivalent Representations of Code By A Self-Reflection Approach](https://mlsanity.com/paper/2410.03351/) (2024)
- [Issue Retrieval and Verification Enhanced Supplementary Code Comment Generation](https://mlsanity.com/paper/2506.14649/) (2025)
- [LibRec: Benchmarking Retrieval-Augmented LLMs for Library Migration Recommendations](https://mlsanity.com/paper/2508.09791/) (2025)
- [Precision in Practice: Knowledge Guided Code Summarizing Grounded in Industrial Expectations](https://mlsanity.com/paper/2602.03400/) (2026)
- [Retrieval-Oriented Code Representations in Agentic Bug Localization](https://mlsanity.com/paper/2607.11046/) (2026)

## Abstract (arXiv)

Existing studies show that code summaries help developers understand and maintain source code. Unfortunately, these summaries are often missing or outdated in software projects. Code summarization aims to generate natural language descriptions automatically for source code. Code summaries are highly structured and have repetitive patterns. Besides the patternized words, a code summary also contains important keywords, which are the key to reflecting the functionality of the code. However, the state-of-the-art approaches perform poorly on predicting the keywords, which leads to the generated summaries suffering a loss in informativeness. To alleviate this problem, this paper proposes a novel retrieve-and-edit approach named EditSum for code summarization. Specifically, EditSum first retrieves a similar code snippet from a pre-defined corpus and treats its summary as a prototype summary to learn the pattern. Then, EditSum edits the prototype automatically to combine the pattern in the prototype with the semantic information of input code. Our motivation is that the retrieved prototype provides a good start-point for post-generation because the summaries of similar code snippets often have the same pattern. The post-editing process further reuses the patternized words in the prototype and generates keywords based on the semantic information of input code. We conduct experiments on a large-scale Java corpus and experimental results demonstrate that EditSum outperforms the state-of-the-art approaches by a substantial margin. The human evaluation also proves the summaries generated by EditSum are more informative and useful. We also verify that EditSum performs well on predicting the patternized words and keywords.