# Are Large Language Models Memorizing Bug Benchmarks?

arXiv: https://arxiv.org/abs/2411.13323 · HTML: https://mlsanity.com/paper/2411.13323/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 20 Nov 2024.

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

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Detecting Pretraining Data from Large Language Models](https://mlsanity.com/paper/2310.16789/) (2023)
- [The Stack: 3 TB of permissively licensed source code](https://mlsanity.com/paper/2211.15533/) (2022)
- [Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models](https://mlsanity.com/paper/2205.10770/) (2022)
- [CodeGemma: Open Code Models Based on Gemma](https://mlsanity.com/paper/2406.11409/) (2024)
- [Benchmarking Benchmark Leakage in Large Language Models](https://mlsanity.com/paper/2404.18824/) (2024)
- [SWE-Bench+: Enhanced Coding Benchmark for LLMs](https://mlsanity.com/paper/2410.06992/) (2024)
- [Large Language Models for Test-Free Fault Localization](https://mlsanity.com/paper/2310.01726/) (2023)
- [Leakage and the Reproducibility Crisis in ML-based Science](https://mlsanity.com/paper/2207.07048/) (2022)
- [RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair](https://mlsanity.com/paper/2312.15698/) (2023)
- [Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation](https://mlsanity.com/paper/2309.10677/) (2023)
- [Large Language Model for Vulnerability Detection: Emerging Results and Future Directions](https://mlsanity.com/paper/2401.15468/) (2024)
- [BugsInPy: A Database of Existing Bugs in Python Programs to Enable Controlled Testing and Debugging Studies](https://mlsanity.com/paper/2401.15481/) (2024)
- [GitBug-Java: A Reproducible Benchmark of Recent Java Bugs](https://mlsanity.com/paper/2402.02961/) (2024)
- [Concerned with Data Contamination? Assessing Countermeasures in Code Language Model](https://mlsanity.com/paper/2403.16898/) (2024)

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

- [The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason](https://mlsanity.com/paper/2506.12286/) (2025)
- [Do LLMs Consider Security? An Empirical Study on Responses to Programming Questions](https://mlsanity.com/paper/2502.14202/) (2025)
- [The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models](https://mlsanity.com/paper/2505.02931/) (2025)
- [Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models](https://mlsanity.com/paper/2504.04372/) (2025)
- [DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information](https://mlsanity.com/paper/2512.24635/) (2025)
- [PatchBench: Evaluating AI Agents for Vulnerability Patching](https://mlsanity.com/paper/2609.04075/) (2026)
- [SnipGen: A Mining Repository Framework for Evaluating LLMs for Code](https://mlsanity.com/paper/2502.07046/) (2025)
- [Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency](https://mlsanity.com/paper/2608.14065/) (2026)
- [Contamination Means Overestimation? A Fine-Grained Empirical Study in Code Intelligence](https://mlsanity.com/paper/2506.02791/) (2025)
- [Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision](https://mlsanity.com/paper/2604.06723/) (2026)
- [A Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair](https://mlsanity.com/paper/2604.21579/) (2026)
- [P2Patch: Exploit-Guided Vulnerability Repair](https://mlsanity.com/paper/2610.20245/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have become integral to various software engineering tasks, including code generation, bug detection, and repair. To evaluate model performance in these domains, numerous bug benchmarks containing real-world bugs from software projects have been developed. However, a growing concern within the software engineering community is that these benchmarks may not reliably reflect true LLM performance due to the risk of data leakage. Despite this concern, limited research has been conducted to quantify the impact of potential leakage. In this paper, we systematically evaluate popular LLMs to assess their susceptibility to data leakage from widely used bug benchmarks. To identify potential leakage, we use multiple metrics, including a study of benchmark membership within commonly used training datasets, as well as analyses of negative log-likelihood and n-gram accuracy. Our findings show that certain models, in particular codegen-multi, exhibit significant evidence of memorization in widely used benchmarks like Defects4J, while newer models trained on larger datasets like LLaMa 3.1 exhibit limited signs of leakage. These results highlight the need for careful benchmark selection and the adoption of robust metrics to adequately assess models capabilities.