mlsanityData to 7 Oct 2026

How Large Language Models are Transforming Machine-Paraphrased Plagiarism

arXiv 2210.03568 ↗First posted 7 Oct 2022cs.CL cs.AIcited by 38

Not on the map. Why?

Abstract (arXiv)

The recent success of large language models for text generation poses a severe threat to academic integrity, as plagiarists can generate realistic paraphrases indistinguishable from original work. However, the role of large autoregressive transformers in generating machine-paraphrased plagiarism and their detection is still developing in the literature. This work explores T5 and GPT-3 for machine-paraphrase generation on scientific articles from arXiv, student theses, and Wikipedia. We evaluate the detection performance of six automated solutions and one commercial plagiarism detection software and perform a human study with 105 participants regarding their detection performance and the quality of generated examples. Our results suggest that large models can rewrite text humans have difficulty identifying as machine-paraphrased (53% mean acc.). Human experts rate the quality of paraphrases generated by GPT-3 as high as original texts (clarity 4.0/5, fluency 4.2/5, coherence 3.8/5). The best-performing detection model (GPT-3) achieves a 66% F1-score in detecting paraphrases.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 25 of its 54 references that are in the map. First posted on arXiv 7 Oct 2022.

Builds on

25 of 54 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2020Scaling Laws for Neural Language Modelscited by 6,411
  6. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  7. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  8. 2020Longformer: The Long-Document Transformercited by 3,362
  9. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 719
  10. 2019Defending Against Neural Fake Newscited by 553
  11. 2018Universal Sentence Encodercited by 485
  12. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
13 more
  1. 2021All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Textcited by 287
  2. 2019Automatic Detection of Generated Text is Easiest when Humans are Fooledcited by 260
  3. 2018The Natural Language Decathlon: Multitask Learning as Question Answeringcited by 235
  4. 2020With Little Power Comes Great Responsibilitycited by 138
  5. 2016Neural Paraphrase Generation with Stacked Residual LSTM Networkscited by 52
  6. 2019Paraphrasing with Large Language Modelscited by 35
  7. 2016Neural Machine Translation with Reconstructioncited by 28
  8. 2021Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detectioncited by 17
  9. 2021Identifying Machine-Paraphrased Plagiarismcited by 16
  10. 2020Testing of Support Tools for Plagiarism Detectioncited by 11
  11. 2022D3: A Massive Dataset of Scholarly Metadata for Analyzing the State of Computer Science Researchcited by 11
  12. 2018Bi-Directional Differentiable Input Reconstruction for Low-Resource Neural Machine Translationcited by 4
  13. 2021Analyzing Non-Textual Content Elements to Detect Academic Plagiarismcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 13; 2024: 11; 2025: 7; 2026: 7.

38 papers.

Sort:

By area:

  1. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  2. 2023Challenges and Applications of Large Language Modelscited by 251
  3. 2023Language Model Behavior: A Comprehensive Surveycited by 92
  4. 2023A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4cited by 81
  5. 2023Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasingcited by 31
  6. 2023A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Textscited by 23
  7. 2024Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challengescited by 18
  8. 2024Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Textcited by 16
  9. 2024Paraphrase Types Elicit Prompt Engineering Capabilitiescited by 15
  10. 2023Paraphrase Detection: Human vs. Machine Contentcited by 12
  11. 2023IMGTB: A Framework for Machine-Generated Text Detection Benchmarkingcited by 12
  12. 2024Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Bettercited by 11
26 more
  1. 2024Improving Black-box Robustness with In-Context Rewritingcited by 8
  2. 2023Academic Writing with GPT-3.5: Reflections on Practices, Efficacy and Transparencycited by 6
  3. 2023Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Modelscited by 6
  4. 2025mdok of KInIT: Robustly Fine-tuned LLM for Binary and Multiclass AI-Generated Text Detectioncited by 6
  5. 2023Reducing Sequence Length by Predicting Edit Operations with Large Language Modelscited by 5
  6. 2024Citation Amnesia: On The Recency Bias of NLP and Other Academic Fieldscited by 5
  7. 2023Paraphrase Types for Generation and Detectioncited by 4
  8. 2024KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text Detectioncited by 4
  9. 2025Detection of LLM-Paraphrased Code and Identification of the Responsible LLM Using Coding Style Featurescited by 4
  10. 2024FOCUS: Forging Originality through Contrastive Use in Self-Plagiarism for Language Modelscited by 3
  11. 2024PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detectioncited by 3
  12. 2026Loci Similes: A Benchmark for Extracting Intertextualities in Latin Literaturecited by 3
  13. 2026Object Hallucination-Free Reinforcement Unlearning for Vision-Language Modelscited by 3
  14. 2024Towards Human Understanding of Paraphrase Types in Large Language Modelscited by 2
  15. 2025Overview of the Plagiarism Detection Task at PAN 2025cited by 2
  16. 2023Paraphrase Acquisition from Image Captionscited by 1
  17. 2024Task-Oriented Paraphrase Analyticscited by 1
  18. 2025Pub-Guard-LLM: Detecting Retracted Biomedical Articles with Reliable Explanationscited by 1
  19. 2025SPADE: Structured Prompting Augmentation for Dialogue Enhancement in Machine-Generated Text Detectioncited by 1
  20. 2025Affect, Body, Cognition, Demographics, and Emotion: The ABCDE of Text Features for Computational Affective Sciencecited by 1
  21. 2026On the Robustness of Machine Unlearning for Vision-Language Modelscited by 1
  22. 2025Teaching and Critiquing Conceptualization and Operationalization in NLPcited by 0
  23. 2026LLM or Human? Perceptions of Trust and Information Quality in Research Summariescited by 0
  24. 2026Variation is the Key: A Variation-Based Framework for LLM-Generated Text Detectioncited by 0
  25. 2026Beyond Representational Similarity: Source-Conditioned Description-Length Gain for Generative Plagiarism Detection and Candidate Source Rerankingcited by 0
  26. 2026Evaluating the Semantic-to-Geometric Gap in Adversarial Defenses Against Vision-Language Model-Based Plagiarismcited by 0