# Distinguishing LLM-generated from Human-written Code by Contrastive Learning

arXiv: https://arxiv.org/abs/2411.04704 · HTML: https://mlsanity.com/paper/2411.04704/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2024.

## Built on by (most cited first, 16 of 16)

- [Token-Importance Guided Direct Preference Optimization](https://mlsanity.com/paper/2505.19653/) (2025)
- [CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings](https://mlsanity.com/paper/2503.13733/) (2025)
- [textttDroid: A Resource Suite for AI-Generated Code Detection](https://mlsanity.com/paper/2507.10583/) (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)
- [Adversarial Contrastive Learning for LLM Quantization Attacks](https://mlsanity.com/paper/2601.02680/) (2026)
- [MultiAIGCD: A Comprehensive dataset for AI Generated Code Detection Covering Multiple Languages, Models,Prompts, and Scenarios](https://mlsanity.com/paper/2507.21693/) (2025)
- [AICD Bench: A Challenging Benchmark for AI-Generated Code Detection](https://mlsanity.com/paper/2602.02079/) (2026)
- [ClarifySTL: An Interactive LLM Agent Framework for STL Transformation through Requirements Clarification](https://mlsanity.com/paper/2605.01209/) (2026)
- [On Developers' Self-Declaration of AI-Generated Code: An Analysis of Practices](https://mlsanity.com/paper/2504.16485/) (2025)
- [Steganography Without Modification: Hidden Communication via LLM Seeds](https://mlsanity.com/paper/2606.09135/) (2026)
- [Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift](https://mlsanity.com/paper/2606.25152/) (2026)
- [code_transformed: The Influence of Large Language Models on Code](https://mlsanity.com/paper/2506.12014/) (2025)
- [Code Fingerprints: Disentangled Attribution of LLM-Generated Code](https://mlsanity.com/paper/2603.04212/) (2026)
- [An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code](https://mlsanity.com/paper/2604.02352/) (2026)
- [HybridCodeAuthorship: A Benchmark Dataset for Line-Level Code Authorship Detection](https://mlsanity.com/paper/2606.12620/) (2026)
- [What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code](https://mlsanity.com/paper/2609.12708/) (2026)

## Abstract (arXiv)

Large language models (LLMs), such as ChatGPT released by OpenAI, have attracted significant attention from both industry and academia due to their demonstrated ability to generate high-quality content for various tasks. Despite the impressive capabilities of LLMs, there are growing concerns regarding their potential risks in various fields, such as news, education, and software engineering. Recently, several commercial and open-source LLM-generated content detectors have been proposed, which, however, are primarily designed for detecting natural language content without considering the specific characteristics of program code. This paper aims to fill this gap by proposing a novel ChatGPT-generated code detector, CodeGPTSensor, based on a contrastive learning framework and a semantic encoder built with UniXcoder. To assess the effectiveness of CodeGPTSensor on differentiating ChatGPT-generated code from human-written code, we first curate a large-scale Human and Machine comparison Corpus (HMCorp), which includes 550K pairs of human-written and ChatGPT-generated code (i.e., 288K Python code pairs and 222K Java code pairs). Based on the HMCorp dataset, our qualitative and quantitative analysis of the characteristics of ChatGPT-generated code reveals the challenge and opportunity of distinguishing ChatGPT-generated code from human-written code with their representative features. Our experimental results indicate that CodeGPTSensor can effectively identify ChatGPT-generated code, outperforming all selected baselines.