# Impact of Code Language Models on Automated Program Repair

arXiv: https://arxiv.org/abs/2302.05020 · HTML: https://mlsanity.com/paper/2302.05020/

## Key facts

- Cited by 85 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2023.

## Built on by (most cited first, 30 of 85)

- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [Magicoder: Empowering Code Generation with OSS-Instruct](https://mlsanity.com/paper/2312.02120/) (2023)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [OctoPack: Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2308.07124/) (2023)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [Is ChatGPT the Ultimate Programming Assistant -- How far is it?](https://mlsanity.com/paper/2304.11938/) (2023)
- [Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)](https://mlsanity.com/paper/2304.06815/) (2023)
- [MarsCode Agent: AI-native Automated Bug Fixing](https://mlsanity.com/paper/2409.00899/) (2024)
- [GPTScan: Detecting Logic Vulnerabilities in Smart Contracts by Combining GPT with Program Analysis](https://mlsanity.com/paper/2308.03314/) (2023)
- [EffiBench: Benchmarking the Efficiency of Automatically Generated Code](https://mlsanity.com/paper/2402.02037/) (2024)
- [NExT: Teaching Large Language Models to Reason about Code Execution](https://mlsanity.com/paper/2404.14662/) (2024)
- [SelfCodeAlign: Self-Alignment for Code Generation](https://mlsanity.com/paper/2410.24198/) (2024)
- [OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs](https://mlsanity.com/paper/2504.04030/) (2025)
- [Bias Testing and Mitigation in LLM-based Code Generation](https://mlsanity.com/paper/2309.14345/) (2023)
- [How Effective Are Neural Networks for Fixing Security Vulnerabilities](https://mlsanity.com/paper/2305.18607/) (2023)
- [Base of RoPE Bounds Context Length](https://mlsanity.com/paper/2405.14591/) (2024)
- [RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair](https://mlsanity.com/paper/2312.15698/) (2023)
- [Calibration and Correctness of Language Models for Code](https://mlsanity.com/paper/2402.02047/) (2024)
- [Large Language Model-Aware In-Context Learning for Code Generation](https://mlsanity.com/paper/2310.09748/) (2023)
- [LeDex: Training LLMs to Better Self-Debug and Explain Code](https://mlsanity.com/paper/2405.18649/) (2024)
- [HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation](https://mlsanity.com/paper/2412.21199/) (2024)
- [HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing](https://mlsanity.com/paper/2412.01778/) (2024)
- [Can Large Language Models Understand Symbolic Graphics Programs?](https://mlsanity.com/paper/2408.08313/) (2024)
- [Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review](https://mlsanity.com/paper/2307.02503/) (2023)
- [EffiLearner: Enhancing Efficiency of Generated Code via Self-Optimization](https://mlsanity.com/paper/2405.15189/) (2024)

## Abstract (arXiv)

Automated program repair (APR) aims to help developers improve software reliability by generating patches for buggy programs. Although many code language models (CLM) are developed and effective in many software tasks such as code completion, there has been little comprehensive, in-depth work to evaluate CLMs' fixing capabilities and to fine-tune CLMs for the APR task. Firstly, this work is the first to evaluate ten CLMs on four APR benchmarks, which shows that surprisingly, the best CLM, as is, fixes 72% more bugs than the state-of-the-art deep-learning (DL)-based APR techniques. Secondly, one of the four APR benchmarks was created by us in this paper to avoid data leaking for a fair evaluation. Thirdly, it is the first work to fine-tune CLMs with APR training data, which shows that fine-tuning brings 31%-1,267% improvement to CLMs and enables them to fix 46%-164% more bugs than existing DL-based APR techniques. Fourthly, this work studies the impact of buggy lines, showing that CLMs, as is, cannot make good use of the buggy lines to fix bugs, yet fine-tuned CLMs could potentially over-rely on buggy lines. Lastly, this work analyzes the size, time, and memory efficiency of different CLMs. This work shows promising directions for the APR domain, such as fine-tuning CLMs with APR-specific designs, and also raises awareness of fair and comprehensive evaluations of CLMs and calls for more transparent reporting of open-source repositories used in the pre-training data to address the data leaking problem.