# DeepMerge: Learning to Merge Programs

arXiv: https://arxiv.org/abs/2105.07569 · HTML: https://mlsanity.com/paper/2105.07569/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2021.

## Built on by (most cited first, 3 of 3)

- [Program Merge Conflict Resolution via Neural Transformers](https://mlsanity.com/paper/2109.00084/) (2021)
- [NeuDep: Neural Binary Memory Dependence Analysis](https://mlsanity.com/paper/2210.02853/) (2022)
- [Merge-Bench: Resolve Merge Conflicts with Large Language Models](https://mlsanity.com/paper/2605.25890/) (2026)

## Abstract (arXiv)

In collaborative software development, program merging is the mechanism to integrate changes from multiple programmers. Merge algorithms in modern version control systems report a conflict when changes interfere textually. Merge conflicts require manual intervention and frequently stall modern continuous integration pipelines. Prior work found that, although costly, a large majority of resolutions involve re-arranging text without writing any new code. Inspired by this observation we propose the first data-driven approach to resolve merge conflicts with a machine learning model. We realize our approach in a tool DeepMerge that uses a novel combination of (i) an edit-aware embedding of merge inputs and (ii) a variation of pointer networks, to construct resolutions from input segments. We also propose an algorithm to localize manual resolutions in a resolved file and employ it to curate a ground-truth dataset comprising 8,719 non-trivial resolutions in JavaScript programs. Our evaluation shows that, on a held out test set, DeepMerge can predict correct resolutions for 37% of non-trivial merges, compared to only 4% by a state-of-the-art semistructured merge technique. Furthermore, on the subset of merges with upto 3 lines (comprising 24% of the total dataset), DeepMerge can predict correct resolutions with 78% accuracy.