# Bugs in Large Language Models Generated Code: An Empirical Study

arXiv: https://arxiv.org/abs/2403.08937 · HTML: https://mlsanity.com/paper/2403.08937/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 87 references that are in the map.
- First posted on arXiv 13 Mar 2024.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [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)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [OctoPack: Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2308.07124/) (2023)
- [ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation](https://mlsanity.com/paper/2308.01861/) (2023)
- [GitHub Copilot AI pair programmer: Asset or Liability?](https://mlsanity.com/paper/2206.15331/) (2022)
- [Large Language Models Meet NL2Code: A Survey](https://mlsanity.com/paper/2212.09420/) (2022)
- [Structured Chain-of-Thought Prompting for Code Generation](https://mlsanity.com/paper/2305.06599/) (2023)
- [PanGu-α: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation](https://mlsanity.com/paper/2104.12369/) (2021)
- [InferFix: End-to-End Program Repair with LLMs](https://mlsanity.com/paper/2303.07263/) (2023)
- [Taxonomy of Real Faults in Deep Learning Systems](https://mlsanity.com/paper/1910.11015/) (2019)
- [Refining ChatGPT-Generated Code: Characterizing and Mitigating Code Quality Issues](https://mlsanity.com/paper/2307.12596/) (2023)
- [Automated Repair of Programs from Large Language Models](https://mlsanity.com/paper/2205.10583/) (2022)
- [Is GitHub's Copilot as Bad as Humans at Introducing Vulnerabilities in Code?](https://mlsanity.com/paper/2204.04741/) (2022)
- [On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot](https://mlsanity.com/paper/2302.00438/) (2023)
- [EffiBench: Benchmarking the Efficiency of Automatically Generated Code](https://mlsanity.com/paper/2402.02037/) (2024)
- [How Novices Use LLM-Based Code Generators to Solve CS1 Coding Tasks in a Self-Paced Learning Environment](https://mlsanity.com/paper/2309.14049/) (2023)
- [PanGu-Coder: Program Synthesis with Function-Level Language Modeling](https://mlsanity.com/paper/2207.11280/) (2022)
- ["What It Wants Me To Say": Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Models](https://mlsanity.com/paper/2304.06597/) (2023)
- [Large Language Models and Simple, Stupid Bugs](https://mlsanity.com/paper/2303.11455/) (2023)
- [CCTEST: Testing and Repairing Code Completion Systems](https://mlsanity.com/paper/2208.08289/) (2022)
- [ChatGPT vs SBST: A Comparative Assessment of Unit Test Suite Generation](https://mlsanity.com/paper/2307.00588/) (2023)

## Built on by (most cited first, 30 of 60)

- [Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code](https://mlsanity.com/paper/2404.00971/) (2024)
- [When LLMs Meet Cybersecurity: A Systematic Literature Review](https://mlsanity.com/paper/2405.03644/) (2024)
- [What's Wrong with Your Code Generated by Large Language Models? An Extensive Study](https://mlsanity.com/paper/2407.06153/) (2024)
- [Type-Constrained Code Generation with Language Models](https://mlsanity.com/paper/2504.09246/) (2025)
- [Correctness Assessment of Code Generated by Large Language Models Using Internal Representations](https://mlsanity.com/paper/2501.12934/) (2025)
- [MdEval: Massively Multilingual Code Debugging](https://mlsanity.com/paper/2411.02310/) (2024)
- [CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation](https://mlsanity.com/paper/2503.22688/) (2025)
- [Rethinking Software Engineering in the Foundation Model Era: From Task-Driven AI Copilots to Goal-Driven AI Pair Programmers](https://mlsanity.com/paper/2404.10225/) (2024)
- [Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges](https://mlsanity.com/paper/2504.20799/) (2025)
- [RAMBO: Enhancing RAG-based Repository-Level Method Body Completion](https://mlsanity.com/paper/2409.15204/) (2024)
- [A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?](https://mlsanity.com/paper/2411.01414/) (2024)
- [Model Editing for LLMs4Code: How Far are We?](https://mlsanity.com/paper/2411.06638/) (2024)
- [Beyond Synthetic Benchmarks: Evaluating LLM Performance on Real-World Class-Level Code Generation](https://mlsanity.com/paper/2510.26130/) (2025)
- [How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests](https://mlsanity.com/paper/2601.17581/) (2026)
- [When Do LLMs Admit Their Mistakes? Understanding The Role Of Model Belief In Retraction](https://mlsanity.com/paper/2505.16170/) (2025)
- [CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs](https://mlsanity.com/paper/2506.11059/) (2025)
- [Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomy](https://mlsanity.com/paper/2603.05637/) (2026)
- [Understanding Defects in Generated Codes by Language Models](https://mlsanity.com/paper/2408.13372/) (2024)
- [IFEvalCode: Controlled Code Generation](https://mlsanity.com/paper/2507.22462/) (2025)
- [Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models](https://mlsanity.com/paper/2504.04372/) (2025)
- [Code Copycat Conundrum: Demystifying Repetition in LLM-based Code Generation](https://mlsanity.com/paper/2504.12608/) (2025)
- [Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMs](https://mlsanity.com/paper/2405.13932/) (2024)
- [TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models](https://mlsanity.com/paper/2407.21227/) (2024)
- [One Step at a Time: Combining LLMs and Static Analysis to Generate Next-Step Hints for Programming Tasks](https://mlsanity.com/paper/2410.09268/) (2024)
- [Deep-Bench: Deep Learning Benchmark Dataset for Code Generation](https://mlsanity.com/paper/2502.18726/) (2025)
- [DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning](https://mlsanity.com/paper/2605.25604/) (2026)
- [Towards Specification-Driven LLM-Based Generation of Embedded Automotive Software](https://mlsanity.com/paper/2411.13269/) (2024)
- [Assessing LLM code generation quality through path planning tasks](https://mlsanity.com/paper/2504.21276/) (2025)
- [A Qualitative Investigation into LLM-Generated Multilingual Code Comments and Automatic Evaluation Metrics](https://mlsanity.com/paper/2505.15469/) (2025)
- [Navigating Pitfalls: Evaluating LLMs in Machine Learning Programming Education](https://mlsanity.com/paper/2505.18220/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) for code have gained significant attention recently. They can generate code in different programming languages based on provided prompts, fulfilling a long-lasting dream in Software Engineering (SE), i.e., automatic code generation. Similar to human-written code, LLM-generated code is prone to bugs, and these bugs have not yet been thoroughly examined by the community. Given the increasing adoption of LLM-based code generation tools (e.g., GitHub Copilot) in SE activities, it is critical to understand the characteristics of bugs contained in code generated by LLMs. This paper examines a sample of 333 bugs collected from code generated using three leading LLMs (i.e., CodeGen, PanGu-Coder, and Codex) and identifies the following 10 distinctive bug patterns: Misinterpretations, Syntax Error, Silly Mistake, Prompt-biased code, Missing Corner Case, Wrong Input Type, Hallucinated Object, Wrong Attribute, Incomplete Generation, and Non-Prompted Consideration. The bug patterns are presented in the form of a taxonomy. The identified bug patterns are validated using an online survey with 34 LLM practitioners and researchers. The surveyed participants generally asserted the significance and prevalence of the bug patterns. Researchers and practitioners can leverage these findings to develop effective quality assurance techniques for LLM-generated code. This study sheds light on the distinctive characteristics of LLM-generated code.