EUVIMEDEUVIMED entdecken
Crossref

Hyperbolic Large Language Models

Sarang Patil, Zeyong Zhang, Yiran Huang, Tengfei Ma, Mengjia Xu

SIAM Review · 31.12.2026 · 68 (4) · 885-913

DOI: 10.1137/25m1795248 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Review, online erschienen am 12.11.2026. Verfasst von Sarang Patil und 4 weiteren Autor:innen. Die Arbeit nennt 84 Literaturangaben. Gefördert von: U.S. Department of Energy SEA-CROGS, Air Force Office of Scientific Research, National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) have achieved remarkable success and demonstrated superior performance across various tasks, including natural language processing (NLP), weather forecasting, biological protein folding, text generation, and solving mathematical problems. However, many real-world data exhibit highly non-Euclidean latent hierarchical anatomy, such as protein networks, transportation networks, financial networks, brain networks, and linguistic structures or syntactic trees in natural languages. Effectively learning intrinsic semantic entailment and hierarchical relationships from these raw, unstructured input data using LLMs remains an underexplored area. Due to its effectiveness in modeling tree-like hierarchical structures, hyperbolic geometry—a non-Euclidean space—has rapidly gained popularity as an expressive latent representation space for complex data modeling across domains such as graphs, images, languages, and multimodal data. Here, we provide a comprehensive and contextual exposition of recent advancements in LLMs that leverage hyperbolic geometry as a representation space to enhance semantic representation learning and multiscale reasoning. Specifically, the paper presents a taxonomy of the principal techniques of hyperbolic LLMs (HypLLMs) in terms of four main categories: (1) hyperbolic LLMs through exp/log maps; (2) hyperbolic fine-tuned models; (3) fully hyperbolic LLMs; and (4) hyperbolic state-space models. We also explore crucial potential applications and outline future research directions. A repository of key papers, models, datasets, and code implementations is available at https://github.com/sarangp2402/Hyperbolic-LLM-Models .

Förderung

  • U.S. Department of Energy SEA-CROGS
  • Air Force Office of Scientific Research
  • National Science Foundation

Zitieren

APA

Patil, S., Zhang, Z., Huang, Y., Ma, T., & Xu, M. (2026). Hyperbolic Large Language Models. SIAM Review, 68(4), 885-913. https://doi.org/10.1137/25m1795248

Vancouver

Patil S, Zhang Z, Huang Y, Ma T, Xu M. Hyperbolic Large Language Models. SIAM Review. 2026;68(4):885-913. doi:10.1137/25m1795248

BibTeX
@article{Patil2026,
  author = {Patil, Sarang and Zhang, Zeyong and Huang, Yiran and Ma, Tengfei and Xu, Mengjia},
  title = {Hyperbolic Large Language Models},
  journal = {SIAM Review},
  year = {2026},
  volume = {68},
  number = {4},
  pages = {885--913},
  doi = {10.1137/25m1795248}
}
Kostenlos starten →