# A Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair

arXiv: https://arxiv.org/abs/2604.21579 · HTML: https://mlsanity.com/paper/2604.21579/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 65 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 30 of 42)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [Don't Make Your LLM an Evaluation Benchmark Cheater](https://mlsanity.com/paper/2311.01964/) (2023)
- [SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair](https://mlsanity.com/paper/1901.01808/) (2018)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation](https://mlsanity.com/paper/1812.08693/) (2018)
- [Benchmarking Benchmark Leakage in Large Language Models](https://mlsanity.com/paper/2404.18824/) (2024)
- [Natural Attack for Pre-trained Models of Code](https://mlsanity.com/paper/2201.08698/) (2022)
- [A Survey of Learning-based Automated Program Repair](https://mlsanity.com/paper/2301.03270/) (2023)
- [Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation](https://mlsanity.com/paper/2309.10677/) (2023)
- [Large Language Model for Vulnerability Detection and Repair: Literature Review and the Road Ahead](https://mlsanity.com/paper/2404.02525/) (2024)
- [A Systematic Literature Review on Large Language Models for Automated Program Repair](https://mlsanity.com/paper/2405.01466/) (2024)
- [LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks](https://mlsanity.com/paper/2502.06215/) (2025)
- [Neural Transfer Learning for Repairing Security Vulnerabilities in C Code](https://mlsanity.com/paper/2104.08308/) (2021)
- [Source Code Summarization in the Era of Large Language Models](https://mlsanity.com/paper/2407.07959/) (2024)
- [A Critical Review of Large Language Model on Software Engineering: An Example from ChatGPT and Automated Program Repair](https://mlsanity.com/paper/2310.08879/) (2023)
- [Traces of Memorisation in Large Language Models for Code](https://mlsanity.com/paper/2312.11658/) (2023)
- [A Survey of LLM-based Automated Program Repair: Taxonomies, Design Paradigms, and Applications](https://mlsanity.com/paper/2506.23749/) (2025)
- [Adversarial Robustness of Deep Code Comment Generation](https://mlsanity.com/paper/2108.00213/) (2021)
- [Hybrid Automated Program Repair by Combining Large Language Models and Program Analysis](https://mlsanity.com/paper/2406.00992/) (2024)

## Abstract (arXiv)

LLM-based automated program repair (APR) techniques have shown promising results in reducing debugging costs. However, prior results can be affected by data leakage: large language models (LLMs) may memorize bug fixes when evaluation benchmarks overlap with their pretraining data, leading to inflated performance estimates. In this paper, we investigate whether we can better reveal data leakage by combining metamorphic testing (MT) with negative log-likelihood (NLL), which has been used in prior work as a proxy for memorization. We construct variant benchmarks by applying semantics-preserving transformations to two widely used datasets, Defects4J and GitBug-Java. Using these benchmarks, we evaluate the repair success rates of seven LLMs on both original and transformed versions, and analyze the relationship between performance degradation and NLL. Our results show that all evaluated state-of-the-art LLMs exhibit substantial drops in patch generation success rates on transformed benchmarks, ranging from -4.1% for GPT-4o to -15.98% for Llama-3.1. Furthermore, we find that this degradation strongly correlates with NLL on the original benchmarks, suggesting that models perform better on instances they are more likely to have memorized. These findings show that combining MT with NLL provides stronger and more reliable evidence of data leakage, while metamorphic testing alone can help mitigate its effects in LLM-based APR evaluations.