# CodeMirage: Hallucinations in Code Generated by Large Language Models

arXiv: https://arxiv.org/abs/2408.08333 · HTML: https://mlsanity.com/paper/2408.08333/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 14 Aug 2024.

## Builds on (most cited first, 24 of 24)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2304.01933/) (2023)
- [Retrieval Augmented Code Generation and Summarization](https://mlsanity.com/paper/2108.11601/) (2021)
- [Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models](https://mlsanity.com/paper/2312.04724/) (2023)
- [An Empirical Study of the Non-determinism of ChatGPT in Code Generation](https://mlsanity.com/paper/2308.02828/) (2023)
- [Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks](https://mlsanity.com/paper/2304.10145/) (2023)
- [The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey](https://mlsanity.com/paper/2104.14839/) (2021)
- [A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems](https://mlsanity.com/paper/2402.18649/) (2024)
- [AI-assisted coding: Experiments with GPT-4](https://mlsanity.com/paper/2304.13187/) (2023)
- [Large Language Models of Code Fail at Completing Code with Potential Bugs](https://mlsanity.com/paper/2306.03438/) (2023)
- [AI in the Gray: Exploring Moderation Policies in Dialogic Large Language Models vs. Human Answers in Controversial Topics](https://mlsanity.com/paper/2308.14608/) (2023)
- [Software Vulnerability and Functionality Assessment using LLMs](https://mlsanity.com/paper/2403.08429/) (2024)
- [HateRephrase: Zero- and Few-Shot Reduction of Hate Intensity in Online Posts using Large Language Models](https://mlsanity.com/paper/2310.13985/) (2023)

## Built on by (most cited first, 23 of 23)

- [Agents in Software Engineering: Survey, Landscape, and Vision](https://mlsanity.com/paper/2409.09030/) (2024)
- [MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models](https://mlsanity.com/paper/2409.19492/) (2024)
- [SetupBench: Assessing Software Engineering Agents' Ability to Bootstrap Development Environments](https://mlsanity.com/paper/2507.09063/) (2025)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods](https://mlsanity.com/paper/2603.21011/) (2026)
- [Bridging LLM Planning Agents and Formal Methods: A Case Study in Plan Verification](https://mlsanity.com/paper/2510.03469/) (2025)
- [PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments](https://mlsanity.com/paper/2605.30880/) (2026)
- [Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality](https://mlsanity.com/paper/2503.05860/) (2025)
- [ALMAS: an Autonomous LLM-based Multi-Agent Software Engineering Framework](https://mlsanity.com/paper/2510.03463/) (2025)
- [The Fools are Certain; the Wise are Doubtful: Exploring LLM Confidence in Code Completion](https://mlsanity.com/paper/2508.16131/) (2025)
- [Securing LLM-Generated Embedded Firmware through AI Agent-Driven Validation and Patching](https://mlsanity.com/paper/2509.09970/) (2025)
- [Delulu: A Verified Multi-Lingual Benchmark for Code Hallucination Detection in Fill-in-the-Middle Tasks](https://mlsanity.com/paper/2605.07024/) (2026)
- [Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and Documents](https://mlsanity.com/paper/2607.00895/) (2026)
- [SOK: Exploring Hallucinations and Security Risks in AI-Assisted Software Development with Insights for LLM Deployment](https://mlsanity.com/paper/2502.18468/) (2025)
- [Chemical classification program synthesis using generative artificial intelligence](https://mlsanity.com/paper/2505.18470/) (2025)
- [From Natural Language to Executable Option Strategies via Large Language Models](https://mlsanity.com/paper/2603.16434/) (2026)
- [Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code](https://mlsanity.com/paper/2605.05267/) (2026)
- [DuoLens: A Framework for Robust Detection of Machine-Generated Multilingual Text and Code](https://mlsanity.com/paper/2510.18904/) (2025)
- [ConceptRM: The Quest to Mitigate Alert Fatigue through Consensus-Based Purity-Driven Data Cleaning for Reflection Modelling](https://mlsanity.com/paper/2602.20166/) (2026)
- [RepoReviewer: A Local-First Multi-Agent Architecture for Repository-Level Code Review](https://mlsanity.com/paper/2603.16107/) (2026)
- [Task Abstention for Large Language Models in Code Generation](https://mlsanity.com/paper/2605.17029/) (2026)
- [Helpful or Harmful? Evaluating LLM-Assisted Vulnerability Patching via a Human Study](https://mlsanity.com/paper/2606.25973/) (2026)
- [Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization](https://mlsanity.com/paper/2609.14839/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have shown promising potentials in program generation and no-code automation. However, LLMs are prone to generate hallucinations, i.e., they generate text which sounds plausible but is incorrect. Although there has been a recent surge in research on LLM hallucinations for text generation, similar hallucination phenomenon can happen in code generation. Sometimes the generated code can have syntactical or logical errors as well as more advanced issues like security vulnerabilities, memory leaks, etc. Given the wide adaptation of LLMs to enhance efficiency in code generation and development in general, it becomes imperative to investigate hallucinations in code generation. To the best of our knowledge, this is the first attempt at studying hallucinations in the code generated by LLMs. We start by introducing the code hallucination definition and a comprehensive taxonomy of code hallucination types. We propose the first benchmark CodeMirage dataset for code hallucinations. The benchmark contains 1,137 GPT-3.5 generated hallucinated code snippets for Python programming problems from two base datasets - HumanEval and MBPP. We then propose the methodology for code hallucination detection and experiment with open source LLMs such as CodeLLaMA as well as OpenAI's GPT-3.5 and GPT-4 models using one-shot prompt. We find that GPT-4 performs the best on HumanEval dataset and gives comparable results to the fine-tuned CodeBERT baseline on MBPP dataset. Towards the end, we discuss various mitigation strategies for code hallucinations and conclude our work.