Evolution and Impact of Large Language Models: A Systematic Review


EOI: 10.11242/viva-tech.01.09.29

Download Full Text here



Citation

Dr. Pradnya Atmaram Mhatre,"Evolution and Impact of Large Language Models: A Systematic Review", VIVA-IJRI Volume 1, Issue 9, Article 29, pp. 1-6, 2026. Published by MCA Department, VIVA Institute of Technology, Virar, India.

Abstract

Large Language Models (LLMs) have revolutionized artificial intelligence (AI) and natural language processing (NLP) by enabling machines to comprehend, produce, and reason with human language in ways that were previously unthinkable. These models are mostly based on the Transformer architecture, which was first presented in 2017 and substitutes self-attention mechanisms that can capture long-range dependencies and contextual linkages in text for recurrent and convolutional techniques. LLMs can now execute a wide range of tasks, including text production, summarization, translation, question answering, and reasoning, frequently with no task-specific training, which has increased over time from millions to billions or even trillions of parameters. The evolution of LLMs from simple Transformer models to contemporary variations is systematically reviewed in this study. I also go over the inherent difficulties of LLMs, such as model bias, hallucinations, high processing demands, and security and ethics issues. Lastly, this analysis highlights the significance of rooting models in factual knowledge while exploring future research possibilities targeted at creating sustainable, effective, and reliable LLMs.

Keywords

factual knowledge, hallucinations, Large Language Models, model bias, Natural Language Processing, Transformer architecture

References

  1. [1] Zhao, W.X.; Zhou, K.; Li, J.; Tang, T.; Wang, X.; Hou, Y.; Min, Y.; Zhang, B.; Zhang, J.;Dong, Z.; et al. A Survey of Large Language Models. arXiv 2024, arXiv:2303.18223.
  2. [2]. Papageorgiou, E.; Chronis, C.; Varlamis, I.; Himeur, Y. A Survey on the Use of Large Language Models (LLMs) in Fake News. Future Internet 2024, 16, 298.
  3. [3] Wang,L.; Ma, C.; Feng, X.; Zhang, Z.; Yang, H.; Zhang, J.; Chen, Z.; Tang, J.; Chen, X.; Lin, Y.; et al. A Survey on Large Language Model Based Autonomous Agents. Front. Comput. Sci. 2024, 18, 186345.
  4. [4] Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, L.; Polosukhin, I. Attention Is All You Need. In Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017)
  5. [5]. Y. Ye, H. You, and J. Du, Improved trust in human-robot collaboration with chatgpt, IEEE Acess, 2023.
  6. [6].Songyue Han, MingyuWang et.al, A Review of Large Language Models: Fundamental Architectures, Key Technological Evolutions, Interdisciplinary Technologies Integration, Optimization and Compression Techniques, Applications, and Challenges, Electronics 2024.9
  7. [7].Sunit Jana1, Rakhi Biswas et.al, The Evolution and Impact of Large Language Model Systems: A Comprehensive Analysis, alochana journal, volume 13 issue 3 2024, ISSN NO: 2231-6329.
  8. [8]. Touvron, H.; Lavril, T.; Izacard, G.; Martinet, X.; Lachaux, M.-A.; Lacroix, T.; Rozière, B.; Goyal, N.; Hambro, E.; Azhar, F.; et al. LLaMA: Open and Efficient Foundation Language Models. arXiv 2023, arXiv:2302.13971.
  9. [9].Devlin, J.; Chang, M.-W.; Lee, K.; Toutanova, K. BERT: Pre-Training of Deep Bidirectional Transformers for Language Understand ing. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT 2019), Minneapolis MN, USA, 2–7 June 2019; Association for Computational Linguistics: Stroudsburg, France, 2019; Volume 1, pp. 4171–4186.
  10. [10].https://www.geeksforgeeks.org/artificial-intelligence/exploring-the-technical-architecture-behind-large-language-models
  11. [11]. Achiam, J.; Adler, S.; Agarwal, S.; Ahmad, L.; Akkaya, I.; Aleman, F.L.; Almeida, D.; Altenschmidt, J.; Altman, S.; Anadkat, S.; et al. GPT-4 Technical Report. arXiv 2024, arXiv:2303.08774.
  12. [12]. Hassanin, M.; Anwar, S.; Radwan, I.; Khan, F.S.; Mian, A. Visual Attention Methods in Deep Learning: An In-Depth Survey. arXiv 2022, arXiv:2204.07756.
  13. [13].Radford, A.; Narasimhan, K. Improving Language Understanding by Generative Pre-Training. 2018.
  14. [14].R. Collobert and J. Weston. A unified architecture for natural language processing: Deep neural networks with multitask learning. In Proceedings of the 25th international conference on Machine learning, pages 160–167. ACM, 2008.
  15. [15].Raiaan, M.A.K.; Mukta, M.S.H.; Fatema, K.; Fahad, N.M.; Sakib, S.; Mim, M.M.J.; Ahmad, J.; Ali, M.E.; Azam, S. A Review on Large Language Models: Architectures, Applications, Taxonomies, Open Issues and Challenges. IEEE Access 2024, 12, 26839–26874.