A Comprehensive Survey of Compression Algorithms for Language Models
ACM Computing Surveys · 31.10.2026 · 58 (14) · 1-35
DOI: 10.1145/3819816 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 27.07.2026. Verfasst von Seungcheol Park und 3 weiteren Autor:innen. Die Arbeit nennt 168 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Institute of Information & communications Technology Planning & Evaluatio, Flexible and Efficient Model Compression Method for Various Applications and Environments, Artificial Intelligence Graduate School Program.
Abstract (Originalsprache)
How can we compress language models without sacrificing accuracy? The number of compression algorithms for language models is rapidly growing to leverage the remarkable advances of recent language models without side effects induced by their gigantic size, including increased carbon emissions, high latency, and restricted usage on resource-constrained mobile devices. While numerous compression algorithms have shown remarkable progress in compressing language models, it ironically becomes challenging to capture emerging trends and identify the fundamental concepts underlying them due to the excessive number of algorithms. In this article, we survey and summarize diverse compression algorithms including pruning, quantization, knowledge distillation, low-rank approximation, and dynamic inference. We not only summarize the overall trend of diverse compression algorithms but also select representative algorithms and provide in-depth analyses of them. Finally, we introduce and discuss promising future research directions.
Förderung
- Institute of Information & communications Technology Planning & Evaluatio
- Flexible and Efficient Model Compression Method for Various Applications and Environments
- Artificial Intelligence Graduate School Program
- AI star Fellowship Support Progra
- Global AI Frontier Lab
- The Institute of Engineering Research at Seoul National University
Zitieren
APA
Park, S., Choi, J., Lee, S., & Kang, U. (2026). A Comprehensive Survey of Compression Algorithms for Language Models. ACM Computing Surveys, 58(14), 1-35. https://doi.org/10.1145/3819816
Vancouver
Park S, Choi J, Lee S, Kang U. A Comprehensive Survey of Compression Algorithms for Language Models. ACM Computing Surveys. 2026;58(14):1-35. doi:10.1145/3819816
BibTeX
@article{Park2026,
author = {Park, Seungcheol and Choi, Jaehyeon and Lee, Sojin and Kang, U},
title = {A Comprehensive Survey of Compression Algorithms for Language Models},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {14},
pages = {1--35},
doi = {10.1145/3819816}
}
EUVIMED