# TransRepair: Context-aware Program Repair for Compilation Errors

arXiv: https://arxiv.org/abs/2210.03986 · HTML: https://mlsanity.com/paper/2210.03986/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2022.

## Built on by (most cited first, 8 of 8)

- [OctoPack: Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2308.07124/) (2023)
- [Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review](https://mlsanity.com/paper/2307.02503/) (2023)
- [Towards an Understanding of Context Utilization in Code Intelligence](https://mlsanity.com/paper/2504.08734/) (2025)
- [Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities](https://mlsanity.com/paper/2212.10017/) (2022)
- [Automated Program Repair: Emerging trends pose and expose problems for benchmarks](https://mlsanity.com/paper/2405.05455/) (2024)
- [Can GPT-O1 Kill All Bugs? An Evaluation of GPT-Family LLMs on QuixBugs](https://mlsanity.com/paper/2409.10033/) (2024)
- [The Impact of Fine-tuning Large Language Models on Automated Program Repair](https://mlsanity.com/paper/2507.19909/) (2025)
- [ComBench: A Repo-level Real-world Benchmark for Compilation Error Repair](https://mlsanity.com/paper/2603.27333/) (2026)

## Abstract (arXiv)

Automatically fixing compilation errors can greatly raise the productivity of software development, by guiding the novice or AI programmers to write and debug code. Recently, learning-based program repair has gained extensive attention and became the state-of-the-art in practice. But it still leaves plenty of space for improvement. In this paper, we propose an end-to-end solution TransRepair to locate the error lines and create the correct substitute for a C program simultaneously. Superior to the counterpart, our approach takes into account the context of erroneous code and diagnostic compilation feedback. Then we devise a Transformer-based neural network to learn the ways of repair from the erroneous code as well as its context and the diagnostic feedback. To increase the effectiveness of TransRepair, we summarize 5 types and 74 fine-grained sub-types of compilations errors from two real-world program datasets and the Internet. Then a program corruption technique is developed to synthesize a large dataset with 1,821,275 erroneous C programs. Through the extensive experiments, we demonstrate that TransRepair outperforms the state-of-the-art in both single repair accuracy and full repair accuracy. Further analysis sheds light on the strengths and weaknesses in the contemporary solutions for future improvement.