Proceedings of International Conference on Applied Innovation in IT  ·  2025/12/22  ·  Vol. 13  ·  Issue 5  ·  pp. 187–191
A Survey of Large and Small Language Models
Bojana Velichkovska, Jasmina Angelevska Kostadinoska, Dushko Stavrov and Goran Jakimovski
📄 Download PDF DOI: 10.25673/122852
Abstract
The design and deployment of language models (LMs) is a significant advancement in the field of natural language processing (NLP). Their strong performance in understanding, interpreting, and generating human language has enabled their applicability in different fields, among which are some extremely sensitive areas as healthcare assistants, drug discovery and medical research, and education. With their potential impact, it is important to understand the way LMs operate and ensure their quality in undertaking these challenges. As such, two different approaches have emerged with specific applicability, namely large (LLMs) and small language models (SLMs). While LLMs have demonstrated high accuracy on generalized knowledge, SLMs have evolved to offer specialized insight for specific domains. Both LMs offer different benefits to their respective users. This study defines and examines the applicability of LLMs and SLMs, names the foundational research behind both, and presents a comparative analysis of the key architectural and methodological innovations and characteristics that have influenced their development, with focus on the newest and most used LMs.
Keywords
Artificial Intelligence Natural Language Processing Large Language Models Small Language Models.
References
  1. P. Johri, S. K. Khatri, A. T. Al-Taani, M. Sabharwal, S. Suvanov, and A. Kumar, “Natural Language Processing: History, Evolution, Application, and Future Work,” Lecture Notes in Networks and Systems, pp. 365–375, 2021, doi: 10.1007/978-981-15-9712-1_31.
  2. B. Ghojogh and A. Ghodsi, “Recurrent Neural Networks and Long Short-Term Memory Networks: Tutorial and Survey,” arXiv, Apr. 22, 2023. Available: https://arxiv.org/abs/2304.11461.
  3. A. Vaswani et al., “Attention Is All You Need,” arXiv, Jun. 12, 2017. Available: https://arxiv.org/abs/1706.03762.
  4. S. Minaee et al., “Large Language Models: A Survey,” arXiv, Feb. 2024, doi: 10.48550/arxiv.2402.06196.
  5. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” arXiv, Oct. 11, 2018. Available: https://arxiv.org/abs/1810.04805.
  6. R. He, A. Ravula, B. Kanagal, J. Ainslie, and G. Research, “RealFormer: Transformer Likes Residual Attention,” Available: https://arxiv.org/pdf/2012.11747.
  7. T. B. Brown et al., “Language Models Are Few-Shot Learners,” arXiv, vol. 4, no. 33, May 2020. Available: https://arxiv.org/abs/2005.14165.
  8. OpenAI, “GPT-4 Technical Report,” arXiv:2303.08774, Mar. 2023, doi: 10.48550/arXiv.2303.08774.
  9. S. Wang, M. Hu, Q. Li, M. Safari, and X. Yang, “Capabilities of GPT-5 on Multimodal Medical Reasoning,” arXiv, 2025. Available: https://arxiv.org/abs/2508.08224.
  10. A. Chowdhery et al., “PaLM: Scaling Language Modeling with Pathways,” arXiv:2204.02311, Apr. 2022. Available: https://arxiv.org/abs/2204.02311.
  11. H. Touvron et al., “LLaMA: Open and Efficient Foundation Language Models,” arXiv:2302.13971, Feb. 2023.
  12. R. Anil et al., “Gemini: A Family of Highly Capable Multimodal Models,” arXiv, Dec. 18, 2023. Available: https://arxiv.org/abs/2312.11805.
  13. DeepSeek-AI et al., “DeepSeek-V3 Technical Report,” arXiv, 2024. Available: https://arxiv.org/abs/2412.19437.
  14. Anthropic, “System Card: Claude Opus 4 & Claude Sonnet 4,” 2025. Available: https://www-cdn.anthropic.com/6d8a8055020700718b0c49369f60816ba2a7c285.pdf.
  15. V. Nguyen et al., “A Survey of Small Language Models,” arXiv, 2024. Available: https://arxiv.org/abs/2410.20011.
  16. V. Sanh, L. Debut, J. Chaumond, and T. Wolf, “DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter,” arXiv, 2019. Available: https://arxiv.org/abs/1910.01108.
  17. Z. Lan, M. Chen, S. Goodman, K. Gimpel, P. Sharma, and R. Soricut, “ALBERT: A Lite BERT for Self-supervised Learning of Language Representations,” arXiv:1909.11942, Feb. 2020. Available: https://arxiv.org/abs/1909.11942.
  18. X. Jiao et al., “TinyBERT: Distilling BERT for Natural Language Understanding,” arXiv:1909.10351, Oct. 2020. Available: https://arxiv.org/abs/1909.10351.
  19. Z. Sun, H. Yu, X. Song, R. Liu, Y. Yang, and D. Zhou, “MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices,” arXiv:2004.02984, Apr. 2020. Available: https://arxiv.org/abs/2004.02984.
  20. W. Wang, F. Wei, L. Dong, H. Bao, N. Yang, and M. Zhou, “MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers,” arXiv:2002.10957, Apr. 2020. Available: https://arxiv.org/abs/2002.10957.
  21. S. Iyer et al., “OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization,” arXiv, Dec. 2022, doi: 10.48550/arxiv.2212.12017.
  22. “Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs,” Databricks, May 05, 2023. Available: https://www.databricks.com/blog/mpt-7b.
  23. A. Hughes, “Phi-2: The surprising power of small language models,” Microsoft Research, Dec. 12, 2023. Available: https://www.microsoft.com/en-us/research/blog/phi-2-the-surprising-power-of-small-language-models/.
  24. Gemma Team et al., “Gemma: Open Models Based on Gemini Research and Technology,” arXiv, Mar. 13, 2024. Available: https://arxiv.org/abs/2403.08295.
  25. A. L. Ben et al., “SmolLM2: When Smol Goes Big — Data-Centric Training of a Small Language Model,” arXiv, 2025. Available: https://arxiv.org/abs/2502.02737.
  26. A. Q. Jiang et al., “Mistral 7B,” arXiv, Oct. 10, 2023. Available: https://arxiv.org/abs/2310.06825.
  27. J. Camilo, “Efficient Strategy for Improving Large Language Model (LLM) Capabilities,” arXiv, 2025. Available: https://www.arxiv.org/abs/2508.04073.
  28. L. Huang et al., “A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions,” arXiv, Nov. 2023, doi: 10.48550/arxiv.2311.05232.
  29. R. Ranjan, S. Gupta, and S. N. Singh, “A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions,” arXiv, 2024. Available: https://arxiv.org/abs/2409.16430.

Proceedings of the International Conference on Applied Innovations in IT by Anhalt University of Applied Sciences is licensed under CC BY-SA 4.0  ·  This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License

ICAIIT 2026
International Conference on Applied Innovation in IT
Navigation
Publisher
ISSN2199-8876
Publisher Edition Hochschule Anhalt
Location Anhalt University of Applied Sciences
Email leiterin.hsb@hs-anhalt.de
Phone +49 (0) 3496 67 5611
Address Building 01, Room 425
Bernburger Str. 55
D-06366 Köthen, Germany
Open Access License
CC BY-SA 4.0

All works are licensed under the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0), unless otherwise noted.

Published by ICAIIT in cooperation with Anhalt University of Applied Sciences.

© 2026 ICAIIT — International Conference on Applied Innovations in IT. Anhalt University of Applied Sciences, Köthen, Germany.
Visitors: site traffic counter