Agha Ali Raza

Publications/Natural Language Processing & LLMs for Low-Resource Languages

Journal · 2025

Urdu Sentential Paraphrased Plagiarism Detection Using Large Language Models

Hafiz Rizwan Iqbal, Muhammad Sharjeel, Jawad Shafi, Usama Mehmood, Agha Ali Raza

ACM TALLIP, vol. 24(9), 2025

Summary

Paraphrasing is an easy way to disguise copied text, and it makes plagiarism much harder to detect, especially in under-resourced languages. We study sentence-level paraphrased plagiarism detection for Urdu, extending our earlier deep-learning architecture with several families of multilingual language models that represent sentences in context. Evaluated on three Urdu benchmark corpora, the approach achieves F1 scores between 92% and 98%, improving on previous state-of-the-art methods and supporting academic integrity tools for Urdu.

Cite this paper

Hafiz Rizwan Iqbal, Muhammad Sharjeel, Jawad Shafi, Usama Mehmood, Agha Ali Raza. Urdu Sentential Paraphrased Plagiarism Detection Using Large Language Models. ACM TALLIP, vol. 24(9), 2025.

@article{iqbal2025urdua,
  author = {Hafiz Rizwan Iqbal and Muhammad Sharjeel and Jawad Shafi and Usama Mehmood and Agha Ali Raza},
  title = {{Urdu Sentential Paraphrased Plagiarism Detection Using Large Language Models}},
  journal = {ACM TALLIP},
  volume = {24},
  number = {9},
  year = {2025},
  url = {https://aghaaliraza.com/publications/2024--TALLIP--Urdu_Sentential_Paraphrased_Plagiarism_Detection_Using_Large_Language_Models.pdf}
}

More on this theme

All 18 works on this theme →