Generalization potential of large language models
Neural Computing and Applications · 2025-02 · 37 (4) · 1973-1997
DOI: 10.1007/s00521-024-10827-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Computing and Applications, online erschienen am 17.12.2024. Verfasst von Mikhail Budnikov und 2 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 152 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Analytical Center for the Government of the Russian Federation, Technische Hochschule Würzburg-Schweinfurt.
Abstract (Originalsprache)
The rise of deep learning techniques and especially the advent of large language models (LLMs) intensified the discussions around possibilities that artificial intelligence with higher generalization capability entails. The range of opinions on the capabilities of LLMs is extremely broad: from equating language models with stochastic parrots to stating that they are already conscious. This paper represents an attempt to review LLM landscape in the context of their generalization capacity as an information theoretic property of those complex systems. We discuss the suggested theoretical explanations for generalization in LLMs and highlight possible mechanisms responsible for these generalization properties. Through an examination of existing literature and theoretical frameworks, we endeavor to provide insights into the mechanisms driving the generalization capacity of LLMs, thus contributing to a deeper understanding of their capabilities and limitations in natural language processing tasks.
Förderung
- Analytical Center for the Government of the Russian Federation
- Technische Hochschule Würzburg-Schweinfurt
Zitieren
APA
Budnikov, M., Bykova, A., & Yamshchikov, I. P. (2025). Generalization potential of large language models. Neural Computing and Applications, 37(4), 1973-1997. https://doi.org/10.1007/s00521-024-10827-6
Vancouver
Budnikov M, Bykova A, Yamshchikov IP. Generalization potential of large language models. Neural Computing and Applications. 2025;37(4):1973-1997. doi:10.1007/s00521-024-10827-6
BibTeX
@article{Budnikov2025,
author = {Budnikov, Mikhail and Bykova, Anna and Yamshchikov, Ivan P.},
title = {Generalization potential of large language models},
journal = {Neural Computing and Applications},
year = {2025},
volume = {37},
number = {4},
pages = {1973--1997},
doi = {10.1007/s00521-024-10827-6}
}
EUVIMED