# Beyond Black Box AI-Generated Plagiarism Detection: From Sentence to Document Level

arXiv: https://arxiv.org/abs/2306.08122 · HTML: https://mlsanity.com/paper/2306.08122/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 13 Jun 2023.

## Builds on (most cited first, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [The Science of Detecting LLM-Generated Texts](https://mlsanity.com/paper/2303.07205/) (2023)
- [A Tutorial on Kernel Density Estimation and Recent Advances](https://mlsanity.com/paper/1704.03924/) (2017)
- [MGTBench: Benchmarking Machine-Generated Text Detection](https://mlsanity.com/paper/2303.14822/) (2023)
- [Will ChatGPT get you caught? Rethinking of Plagiarism Detection](https://mlsanity.com/paper/2302.04335/) (2023)
- [ChatGPT in the Classroom: An Analysis of Its Strengths and Weaknesses for Solving Undergraduate Computer Science Questions](https://mlsanity.com/paper/2304.14993/) (2023)
- [AI, write an essay for me: A large-scale comparison of human-written versus ChatGPT-generated essays](https://mlsanity.com/paper/2304.14276/) (2023)

## Built on by (most cited first, 10 of 10)

- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices](https://mlsanity.com/paper/2403.12503/) (2024)
- [A Multi-Task Evaluation of LLMs' Processing of Academic Text Input](https://mlsanity.com/paper/2508.11779/) (2025)
- [Beyond Traditional Teaching: The Potential of Large Language Models and Chatbots in Graduate Engineering Education](https://mlsanity.com/paper/2309.13059/) (2023)
- [TrustAI at SemEval-2024 Task 8: A Comprehensive Analysis of Multi-domain Machine Generated Text Detection Techniques](https://mlsanity.com/paper/2403.16592/) (2024)
- [Detecting AI-Generated Texts in Cross-Domains](https://mlsanity.com/paper/2410.13966/) (2024)
- [ConvNLP: Image-based AI Text Detection](https://mlsanity.com/paper/2407.07225/) (2024)
- [CL2GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error Correction](https://mlsanity.com/paper/2509.13672/) (2025)
- [Detecting undisclosed LLM-generated content in parliamentary texts](https://mlsanity.com/paper/2606.14209/) (2026)

## Abstract (arXiv)

The increasing reliance on large language models (LLMs) in academic writing has led to a rise in plagiarism. Existing AI-generated text classifiers have limited accuracy and often produce false positives. We propose a novel approach using natural language processing (NLP) techniques, offering quantifiable metrics at both sentence and document levels for easier interpretation by human evaluators. Our method employs a multi-faceted approach, generating multiple paraphrased versions of a given question and inputting them into the LLM to generate answers. By using a contrastive loss function based on cosine similarity, we match generated sentences with those from the student's response. Our approach achieves up to 94% accuracy in classifying human and AI text, providing a robust and adaptable solution for plagiarism detection in academic settings. This method improves with LLM advancements, reducing the need for new model training or reconfiguration, and offers a more transparent way of evaluating and detecting AI-generated text.