A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness
ACM Transactions on Intelligent Systems and Technology · 31.12.2025 · 16 (6) · 1-87
DOI: 10.1145/3768165 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 24.11.2025. Verfasst von Fali Wang und 13 weiteren Autor:innen. Die Arbeit wurde bisher 108-mal zitiert (Crossref) und nennt 467 Literaturangaben. Gefördert von: Army Research Office, Department of Homeland Security CINA, Cisco Faculty Research Award.
Abstract (Originalsprache)
Large language models (LLMs) have demonstrated emergent abilities in text generation, question answering, and reasoning, facilitating various tasks and domains. Despite their proficiency in various tasks, LLMs like PaLM 540B and Llama-3.1 405B face limitations due to large parameter sizes and computational demands, often requiring cloud API use, which raises privacy concerns, limits real-time applications on edge devices, and increases fine-tuning costs. Additionally, LLMs often underperform in specialized domains such as healthcare and law due to insufficient domain-specific knowledge, necessitating specialized models. Therefore, Small Language Models (SLMs) are increasingly favored for their low inference latency, cost-effectiveness, efficient development, and easy customization and adaptability. These models are particularly well-suited for resource-limited environments and domain knowledge acquisition, addressing LLMs’ challenges and proving ideal for applications that require localized data handling for privacy, minimal inference latency for efficiency, and domain knowledge acquisition through lightweight fine-tuning. The rising demand for SLMs has spurred extensive research and development. However, a comprehensive survey investigating issues related to the definition, acquisition, application, enhancement, and reliability of SLM remains lacking, prompting us to conduct a detailed survey on these topics. The definition of SLMs varies widely; thus, to standardize, we propose defining SLMs by their capability to perform specialized tasks and suitability for resource-constrained settings, setting boundaries based on the minimal size for emergent abilities and the maximum size sustainable under resource constraints. For other aspects, we provide a taxonomy of relevant models/methods and develop general frameworks for each category to enhance and utilize SLMs effectively. We have compiled the collected SLM models and related methods on GitHub: https://github.com/FairyFali/SLMs-Survey .
Förderung
- Army Research Office
- Department of Homeland Security CINA
- Cisco Faculty Research Award
Zitieren
APA
Wang, F., Zhang, Z., Zhang, X., Wu, Z., Mo, T., Lu, Q., Wang, W., Li, R., Xu, J., Tang, X., He, Q., Ma, Y., Huang, M., & Wang, S. (2025). A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness. ACM Transactions on Intelligent Systems and Technology, 16(6), 1-87. https://doi.org/10.1145/3768165
Vancouver
Wang F, Zhang Z, Zhang X, Wu Z, Mo T, Lu Q, et al. A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness. ACM Transactions on Intelligent Systems and Technology. 2025;16(6):1-87. doi:10.1145/3768165
BibTeX
@article{Wang2025,
author = {Wang, Fali and Zhang, Zhiwei and Zhang, Xianren and Wu, Zongyu and Mo, TzuHao and Lu, Qiuhao and Wang, Wanjing and Li, Rui and Xu, Junjie and Tang, Xianfeng and He, Qi and Ma, Yao and Huang, Ming and Wang, Suhang},
title = {A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness},
journal = {ACM Transactions on Intelligent Systems and Technology},
year = {2025},
volume = {16},
number = {6},
pages = {1--87},
doi = {10.1145/3768165}
}
EUVIMED