{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T04:12:17Z","timestamp":1776312737128,"version":"3.50.1"},"reference-count":37,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T00:00:00Z","timestamp":1756339200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Palestine Technical University Kadoorie and Al Maqdisi Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>This study aims to conduct a comprehensive comparative evaluation of three transformer-based models, PEGASUS, BART, and T5 variants (SMALL and BASE), for the task of abstractive text summarization. The evaluation spans across three benchmark datasets: CNN\/DailyMail (long-form news articles), Xsum (extreme single-sentence summaries of BBC articles), and Samsum (conversational dialogues). Each dataset presents unique challenges in terms of length, style, and domain, enabling a robust assessment of the models\u2019 capabilities. All models were fine-tuned under controlled experimental settings using filtered and preprocessed subsets, with token length limits applied to maintain consistency and prevent truncation. The evaluation leveraged ROUGE-1, ROUGE-2, and ROUGE-L scores to measure summary quality, while efficiency metrics such as training time were also considered. An additional qualitative assessment was conducted through expert human evaluation of fluency, relevance, and conciseness. Results indicate that PEGASUS achieved the highest ROUGE scores on CNN\/DailyMail, BART excelled in Xsum and Samsum, while T5 models, particularly T5-Base, narrowed the performance gap with larger models while still offering efficiency advantages compared to PEGASUS and BART. These findings highlight the trade-offs between model performance and computational efficiency, offering practical insights into model scaling\u2014where T5-Small favors lightweight efficiency and T5-Base provides stronger accuracy without excessive resource demands.<\/jats:p>","DOI":"10.3390\/fi17090389","type":"journal-article","created":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T15:03:14Z","timestamp":1756393394000},"page":"389","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A Comparative Study of PEGASUS, BART, and T5 for Text Summarization Across Diverse Datasets"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8986-4232","authenticated-orcid":false,"given":"Eman","family":"Daraghmi","sequence":"first","affiliation":[{"name":"Department of Computer Science, Palestine Technical University Kadoorie, Jaffa Street, Tulkarm 9993400, Palestine"}]},{"given":"Lour","family":"Atwe","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Palestine Technical University Kadoorie, Jaffa Street, Tulkarm 9993400, Palestine"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0180-345X","authenticated-orcid":false,"given":"Areej","family":"Jaber","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Palestine Technical University Kadoorie, Jaffa Street, Tulkarm 9993400, Palestine"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Chouikhi, H., and Alsuhaibani, M. (2022). Deep Transformer Language Models for Arabic Text Summarization: A Comparison Study. Appl. Sci., 12.","DOI":"10.3390\/app122311944"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Kotkar, A.D., Mahadik, R.S., More, P.G., and Thorat, S.A. (2024, January 23\u201324). Comparative Analysis of Transformer-Based Large Language Models (LLMs) for Text Summarization. Proceedings of the 2024 1st International Conference on Advanced Computing and Emerging Technologies (ACET), Ghaziabad, India.","DOI":"10.1109\/ACET61898.2024.10730348"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Asmitha, M., Kavitha, C.R., and Radha, D. (2024, January 21\u201323). Summarizing News: Unleashing the Power of BART, GPT-2, T5, and Pegasus Models in Text Summarization. Proceedings of the 2024 4th International Conference on Intelligent Technologies (CONIT), Bangalore, India.","DOI":"10.1109\/CONIT61985.2024.10626617"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Daraghmi, E.Y., and Ming, Y.S. (2012, January 3). Using Graph Theory to Re-Verify the Small World Theory in an Online Social Network Word. Proceedings of the 14th International Conference on Information Integration and Web-Based Applications & Services, Bali, Indonesia.","DOI":"10.1145\/2428736.2428811"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/j.chb.2013.09.014","article-title":"We Are so Close, Less than 4 Degrees Separating You and Me!","volume":"30","author":"Daraghmi","year":"2014","journal-title":"Comput. Hum. Behav."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Duridi, T., Atwe, L., Jaber, A., Daraghmi, E., and Mart\u00ednez, P. (2025, January 16\u201318). Detection of Propaganda and Bias in Social Media: A Case Study of the Israel-Gaza War (2023). Proceedings of the 2025 International Conference on New Trends in Computing Sciences (ICTCS), Amman, Jordan.","DOI":"10.1109\/ICTCS65341.2025.10989479"},{"key":"ref_7","first-page":"194","article-title":"Text Summarization Using Deep Learning Techniques: A Review","volume":"59","author":"Saiyyad","year":"2024","journal-title":"Eng. Proc."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Kolhatkar, G., Paranjape, A., Gokhale, O., and Kadam, D. (2023, January 13). Team Converge at ProbSum 2023: Abstractive Text Summarization of Patient Progress Notes. Proceedings of the 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, Toronto, ON, Canada.","DOI":"10.18653\/v1\/2023.bionlp-1.50"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Fersini, E., Passarotti, M., and Patti, V. (2022, January 26\u201328). WITS: Wikipedia for Italian Text Summarization. Proceedings of the Eighth Italian Conference on Computational Linguistics CliC-it 2021, Milan, Italy.","DOI":"10.4000\/books.aaccademia.10417"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Patwardhan, N., Marrone, S., and Sansone, C. (2023). Transformers in the Real World: A Survey on NLP Applications. Information, 14.","DOI":"10.3390\/info14040242"},{"key":"ref_11","first-page":"j39","article-title":"Text summarization using pre-trained model (pegasus, bert, simple-t5)","volume":"10","author":"Sonar","year":"2023","journal-title":"Int. J. Emerg. Technol. Innov. Res."},{"key":"ref_12","unstructured":"Zhang, J., Zhao, Y., Saleh, M., and Liu, P.J. (2019). PEGASUS: Pre-Training with Extracted Gap-Sentences for Abstractive Summarization. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wang, M., Xie, P., Du, Y., and Hu, X. (2023). T5-Based Model for Abstractive Summarization: A Semi-Supervised Learning Approach with Consistency Loss Functions. Appl. Sci., 13.","DOI":"10.3390\/app13127111"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"13248","DOI":"10.1109\/ACCESS.2021.3052783","article-title":"A Survey of the State-of-the-Art Models in Neural Abstractive Text Summarization","volume":"9","author":"Syed","year":"2021","journal-title":"IEEE Access"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Siragusa, G., and Robaldo, L. (2022). Sentence Graph Attention for Content-Aware Summarization. Appl. Sci., 12.","DOI":"10.3390\/app122010382"},{"key":"ref_16","unstructured":"Barzilay, R., and Kan, M.-Y. (August, January 30). Get to the Point: Summarization with Pointer-Generator Networks. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vancouver, BC, Canada."},{"key":"ref_17","unstructured":"Plummer, D.C., and Mesaglio, M. (2023). The 4 Trends That Prevail on the Gartner Top 10 Strategic Technology Trends for 2024. Gartner."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Quatra, M., and Cagliero, L. (2022). BART-IT: An Efficient Sequence-to-Sequence Model for Italian Text Summarization. Future Internet, 15.","DOI":"10.3390\/fi15010015"},{"key":"ref_19","first-page":"847","article-title":"Summarizing Business News: Evaluating BART, T5, and PEGASUS for Effective Information Extraction","volume":"38","author":"Dharrao","year":"2024","journal-title":"Rev. Intell. Artif."},{"key":"ref_20","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention Is All You Need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Alsuhaibani, M. (2023, January 3\u20135). Fine-Tuned PEGASUS: Exploring the Performance of the Transformer-Based Model on a Diverse Text Summarization Dataset. Proceedings of the 9th World Congress on Electrical Engineering and Computer Systems and Science, London, UK.","DOI":"10.11159\/cist23.117"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zhang, X., Hua, J., and Shen, W. (2021, January 17). Multi-Featured Cyberbullying Detection Based on Deep Learning. Proceedings of the 2021 16th International Conference on Computer Science & Education (ICCSE), Lancaster, UK.","DOI":"10.1109\/ICCSE51940.2021.9569270"},{"key":"ref_23","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., and Zettlemoyer, L. (2019). BART: Denoising Sequence-to-Sequence Pre-Training for Natural Language Generation, Translation, and Comprehension. arXiv.","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref_25","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019, January 2\u20137). BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA."},{"key":"ref_26","first-page":"9","article-title":"Language Models Are Unsupervised Multitask Learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref_27","first-page":"249","article-title":"Recent Advancements in Machine Learning for Cybercrime Prediction","volume":"65","author":"Elluri","year":"2023","journal-title":"J. Comput. Inf. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Verma, S., and Nidhi, V. (2017). Extractive Summarization Using Deep Learning. arXiv.","DOI":"10.13053\/rcs-147-10-9"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"301","DOI":"10.32604\/jai.2024.054314","article-title":"A Comprehensive Overview and Comparative Analysis on Deep Learning Models","volume":"6","author":"Perumal","year":"2024","journal-title":"J. Artif. Intell."},{"key":"ref_30","unstructured":"Bouamor, H., Pino, J., and Bali, K. (2023, January 9\u201314). Inverse Reinforcement Learning for Text Summarization. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, Toronto, ON, Canada."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Allahyari, M., Pouriyeh, S., Assefi, M., Safaei, S., Trippe, E.D., Gutierrez, J.B., and Kochut, K. (2017). Text Summarization Techniques: A Brief Survey. arXiv.","DOI":"10.14569\/IJACSA.2017.081052"},{"key":"ref_32","first-page":"81","article-title":"Semi-Supervised Learning: A Brief Review","volume":"7","author":"Viswanath","year":"2018","journal-title":"Int. J. Eng. Technol."},{"key":"ref_33","unstructured":"Rauniyar, S. (2020, January 26\u201328). A Survey on Deep Learning Based Various Methods Analysis of Text Summarization. Proceedings of the Proceedings of the 2020 International Conference on Inventive Computation Technologies (ICICT), Coimbatore, India."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Nallapati, R., Zhou, B., Santos, C.N., Gulcehre, C., and Xiang, B. (2016). Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond. arXiv.","DOI":"10.18653\/v1\/K16-1028"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Narayan, S., Cohen, S.B., and Lapata, M. (November, January 21). Don\u2019t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium.","DOI":"10.18653\/v1\/D18-1206"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Gliwa, B., Mochol, I., Biesek, M., and Wawer, A. (2019, January 4). Samsum Corpus: A Human-Annotated Dialogue Dataset for Abstractive Summarization. Proceedings of the 2nd Workshop on New Frontiers in Summarization, Hong Kong.","DOI":"10.18653\/v1\/D19-5409"},{"key":"ref_37","unstructured":"Koehn, P. (2004, January 25\u201326). Statistical Significance Tests for Machine Translation Evaluation. Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, Barcelona, Spain."}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/9\/389\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:34:49Z","timestamp":1760034889000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/17\/9\/389"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,28]]},"references-count":37,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["fi17090389"],"URL":"https:\/\/doi.org\/10.3390\/fi17090389","relation":{},"ISSN":["1999-5903"],"issn-type":[{"value":"1999-5903","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,28]]}}}