TY - JOUR AU - Dube, Parijat AB - Abstract: 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. TI - Beyond Black Box AI-Generated Plagiarism Detection: From Sentence to Document Level JF - Computing Research Repository DO - 10.48550/arxiv.2306.08122 DA - 2023-06-13 UR - https://www.deepdyve.com/lp/arxiv-cornell-university/beyond-black-box-ai-generated-plagiarism-detection-from-sentence-to-iTNvJ4sEcX VL - 2023 IS - 2306 DP - DeepDyve ER -