# Aligning the Objective of LLM-based Program Repair

arXiv: https://arxiv.org/abs/2404.08877 · HTML: https://mlsanity.com/paper/2404.08877/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 76 references that are in the map.
- First posted on arXiv 13 Apr 2024.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair](https://mlsanity.com/paper/1901.01808/) (2018)
- [Practical Program Repair in the Era of Large Pre-trained Language Models](https://mlsanity.com/paper/2210.14179/) (2022)
- [Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections](https://mlsanity.com/paper/2104.04670/) (2021)
- [InferFix: End-to-End Program Repair with LLMs](https://mlsanity.com/paper/2303.07263/) (2023)
- [CURE: Code-Aware Neural Machine Translation for Automatic Program Repair](https://mlsanity.com/paper/2103.00073/) (2021)
- [Impact of Code Language Models on Automated Program Repair](https://mlsanity.com/paper/2302.05020/) (2023)
- [Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning](https://mlsanity.com/paper/2207.08281/) (2022)
- [DebugBench: Evaluating Debugging Capability of Large Language Models](https://mlsanity.com/paper/2401.04621/) (2024)
- [Automated Repair of Programs from Large Language Models](https://mlsanity.com/paper/2205.10583/) (2022)
- [Repair Is Nearly Generation: Multilingual Program Repair with LLMs](https://mlsanity.com/paper/2208.11640/) (2022)
- [TBar: Revisiting Template-based Automated Program Repair](https://mlsanity.com/paper/1903.08409/) (2019)
- [A Syntax-Guided Edit Decoder for Neural Program Repair](https://mlsanity.com/paper/2106.08253/) (2021)
- [A Survey of Learning-based Automated Program Repair](https://mlsanity.com/paper/2301.03270/) (2023)
- [Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair](https://mlsanity.com/paper/2309.00608/) (2023)
- [Neural Program Repair with Execution-based Backpropagation](https://mlsanity.com/paper/2105.04123/) (2021)
- [RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair](https://mlsanity.com/paper/2309.06057/) (2023)
- [Conversational Automated Program Repair](https://mlsanity.com/paper/2301.13246/) (2023)

## Built on by (most cited first, 12 of 12)

- [Repo2Run: Automated Building Executable Environment for Code Repository at Scale](https://mlsanity.com/paper/2502.13681/) (2025)
- [Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing](https://mlsanity.com/paper/2506.16136/) (2025)
- [TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code](https://mlsanity.com/paper/2602.06875/) (2026)
- [DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information](https://mlsanity.com/paper/2512.24635/) (2025)
- [FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair](https://mlsanity.com/paper/2603.17826/) (2026)
- [QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization](https://mlsanity.com/paper/2604.05963/) (2026)
- [REFLEX: Reflective Evolution from LLM Experience](https://mlsanity.com/paper/2606.16496/) (2026)
- [From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs](https://mlsanity.com/paper/2506.13182/) (2025)
- [Collaborative Agents for Automated Program Repair in Ruby](https://mlsanity.com/paper/2511.03925/) (2025)
- [Coding in a Bubble? Evaluating LLMs in Resolving Context Adaptation Bugs During Code Adaptation](https://mlsanity.com/paper/2601.06497/) (2026)
- [AdaptAgent: A Multi-agent, Domain-Guided Reasoning Framework for Code Adaptation](https://mlsanity.com/paper/2608.04459/) (2026)
- [Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair](https://mlsanity.com/paper/2609.00854/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have achieved decent results on automated program repair (APR). However, the next token prediction training objective of decoder-only LLMs (e.g., GPT-4) is misaligned with the masked span prediction objective of current infilling-style methods, which impedes LLMs from fully leveraging pre-trained knowledge for program repair. In addition, while some LLMs can locate and repair bugs in certain functions using the related artifacts (e.g., test cases), existing methods still depend on statement-level fault localization methods to provide a list of buggy hunks for repair. This restriction hinders LLMs from exploring potential patches beyond the given locations. In this paper, we investigate a new approach to adapt LLMs to program repair. Our core insight is that LLM's APR capability can be greatly improved by simply aligning the output to their training objective and allowing them to refine the whole program without first identifying faulty statements. Based on this insight, we designed D4C, a straightforward prompting framework for APR. D4C can repair 180 bugs correctly in Defects4J, with each patch being sampled only 10 times. This surpasses the SOTA APR methods with perfect fault localization by 10% and reduces the patch sampling number by 90%. Our findings reveal that (1) objective alignment is crucial for fully exploiting LLM's pre-trained capability, and (2) replacing the traditional localize-buggy-hunks-then-repair workflow with direct debugging is more effective for LLM-based APR methods. Thus, we believe this paper introduces a new mindset for harnessing LLMs in APR.