The power of text similarity in identifying AI-LLM paraphrased documents: The case of BBC news articles and ChatGPT

• URL: http://arxiv.org/abs/2505.12405v1
• Date: Sun, 18 May 2025 13:16:30 GMT
• Title: The power of text similarity in identifying AI-LLM paraphrased documents: The case of BBC news articles and ChatGPT
• Authors: Konstantinos Xylogiannopoulos, Petros Xanthopoulos, Panagiotis Karampelas, Georgios Bakamitsos,
• Abstract summary: We demonstrate the ability of pattern-based similarity detection for AI paraphrased news recognition.<n>We propose an algorithmic scheme, which is not limited to detect whether an article is an AI paraphrase, but, more importantly, to identify that the source of infringement is the ChatGPT.<n>Results show that our pattern similarity-based method, that makes no use of deep learning, can detect ChatGPT assisted paraphrased articles at percentages 96.23% for accuracy, 96.25% for precision, 96.21% for sensitivity, 96.25% for specificity and 96.23% for F1 score.
• Score: 2.024925013349319
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Generative AI paraphrased text can be used for copyright infringement and the AI paraphrased content can deprive substantial revenue from original content creators. Despite this recent surge of malicious use of generative AI, there are few academic publications that research this threat. In this article, we demonstrate the ability of pattern-based similarity detection for AI paraphrased news recognition. We propose an algorithmic scheme, which is not limited to detect whether an article is an AI paraphrase, but, more importantly, to identify that the source of infringement is the ChatGPT. The proposed method is tested with a benchmark dataset specifically created for this task that incorporates real articles from BBC, incorporating a total of 2,224 articles across five different news categories, as well as 2,224 paraphrased articles created with ChatGPT. Results show that our pattern similarity-based method, that makes no use of deep learning, can detect ChatGPT assisted paraphrased articles at percentages 96.23% for accuracy, 96.25% for precision, 96.21% for sensitivity, 96.25% for specificity and 96.23% for F1 score.

Related papers

• Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection [71.59834293521074]
  We develop a framework to distinguish between human-authored and machine-generated text.<n>Our method achieves 98.3% AUROC and AUPR with only 8.9% FPR95 on DeepFake dataset.<n>Code, pretrained weights, and demo will be released.
  arXiv  Detail & Related papers  (2025-10-07T08:14:45Z)
• Evaluating the Performance of AI Text Detectors, Few-Shot and Chain-of-Thought Prompting Using DeepSeek Generated Text [2.942616054218564]
  Adrialversa attacks, such as standard and humanized paraphrasing, inhibit detectors' ability to detect text.<n>We investigate whether six generally accessible AI Text, Content Detector AI, Copyleaks, QuillBot, GPT-2, and GPTZero can consistently recognize text generated by DeepSeek.
  arXiv  Detail & Related papers  (2025-07-23T21:26:33Z)
• Assessing GPTZero's Accuracy in Identifying AI vs. Human-Written Essays [0.0]
  GPTZero is the most-used AI detector, but its reliability in distinguishing human-authored texts is limited.<n>A vast majority of the AI-generated papers were detected accurately (ranging from 91-100% AI believed generation), while the human generated essays fluctuated.<n>These findings suggest that although GPTZero is effective at detecting purely AI-generated content, its reliability in distinguishing human-authored texts is limited.
  arXiv  Detail & Related papers  (2025-06-30T04:53:27Z)
• AuthorMist: Evading AI Text Detectors with Reinforcement Learning [4.806579822134391]
  AuthorMist is a novel reinforcement learning-based system to transform AI-generated text into human-like writing.<n>We show that AuthorMist effectively reduces the detectability of AI-generated text while preserving the original meaning.
  arXiv  Detail & Related papers  (2025-03-10T12:41:05Z)
• Generative AI in Academic Writing: A Comparison of DeepSeek, Qwen, ChatGPT, Gemini, Llama, Mistral, and Gemma [0.9562145896371785]
  Free and open-source models offer significant potential for academic writing and content creation.<n>This study evaluates their academic writing performance by comparing them with ChatGPT, Gemini, Llama, Mistral, and Gemma.<n>The generated content was analyzed using plagiarism detection, AI detection, word count comparisons, semantic similarity, and readability assessments.
  arXiv  Detail & Related papers  (2025-02-11T18:33:22Z)
• Group-Adaptive Threshold Optimization for Robust AI-Generated Text Detection [60.09665704993751]
  We introduce FairOPT, an algorithm for group-specific threshold optimization for probabilistic AI-text detectors.<n>Our framework paves the way for more robust classification in AI-generated content detection via post-processing.
  arXiv  Detail & Related papers  (2025-02-06T21:58:48Z)
• Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Text [61.22649031769564]
  We propose a novel framework, paraphrased text span detection (PTD) PTD aims to identify paraphrased text spans within a text. We construct a dedicated dataset, PASTED, for paraphrased text span detection.
  arXiv  Detail & Related papers  (2024-05-21T11:22:27Z)
• DEMASQ: Unmasking the ChatGPT Wordsmith [63.8746084667206]
  We propose an effective ChatGPT detector named DEMASQ, which accurately identifies ChatGPT-generated content. Our method addresses two critical factors: (i) the distinct biases in text composition observed in human- and machine-generated content and (ii) the alterations made by humans to evade previous detection methods.
  arXiv  Detail & Related papers  (2023-11-08T21:13:05Z)
• Distinguishing Human Generated Text From ChatGPT Generated Text Using Machine Learning [0.251657752676152]
  This paper presents a machine learning-based solution that can identify the ChatGPT delivered text from the human written text. We have tested the proposed model on a Kaggle dataset consisting of 10,000 texts out of which 5,204 texts were written by humans and collected from news and social media. On the corpus generated by GPT-3.5, the proposed algorithm presents an accuracy of 77%.
  arXiv  Detail & Related papers  (2023-05-26T09:27:43Z)
• DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection [56.513637720967566]
  Large language models (LLMs) can generate texts that pose risks of misuse, such as plagiarism, planting fake reviews on e-commerce platforms, or creating inflammatory false tweets. Existing high-quality detection methods usually require access to the interior of the model to extract the intrinsic characteristics. We propose to extract deep intrinsic characteristics of the black-box model generated texts.
  arXiv  Detail & Related papers  (2023-05-21T17:26:16Z)
• On the Possibilities of AI-Generated Text Detection [76.55825911221434]
  We argue that as machine-generated text approximates human-like quality, the sample size needed for detection bounds increases. We test various state-of-the-art text generators, including GPT-2, GPT-3.5-Turbo, Llama, Llama-2-13B-Chat-HF, and Llama-2-70B-Chat-HF, against detectors, including oBERTa-Large/Base-Detector, GPTZero.
  arXiv  Detail & Related papers  (2023-04-10T17:47:39Z)
• Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense [56.077252790310176]
  We present a paraphrase generation model (DIPPER) that can paraphrase paragraphs, condition on surrounding context, and control lexical diversity and content reordering. Using DIPPER to paraphrase text generated by three large language models (including GPT3.5-davinci-003) successfully evades several detectors, including watermarking. We introduce a simple defense that relies on retrieving semantically-similar generations and must be maintained by a language model API provider.
  arXiv  Detail & Related papers  (2023-03-23T16:29:27Z)
• Verifying the Robustness of Automatic Credibility Assessment [50.55687778699995]
  We show that meaning-preserving changes in input text can mislead the models. We also introduce BODEGA: a benchmark for testing both victim models and attack methods on misinformation detection tasks. Our experimental results show that modern large language models are often more vulnerable to attacks than previous, smaller solutions.
  arXiv  Detail & Related papers  (2023-03-14T16:11:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.