Preprint · 2025 · Open access

Uncovering Hierarchical Structure in LLM Embeddings Using Geometric and Topological Measures

Prakash Chourasia, Sarwan Ali, Murray Patterson, Alex Zelikovsky

arXiv (Cornell University) · Published 24 December 2025 · DOI 10.48550/arxiv.2512.20926

Open PDFView at the publisherCite this paper

In brief

“Uncovering Hierarchical Structure in LLM Embeddings Using Geometric and Topological Measures” is a 2025 preprint by Prakash Chourasia and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY-NC-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
0
References
38
Authors
4

Abstract

The rapid advancement of large language models (LLMs) has driven major advances across scientific domains, yet the hierarchical, geometric, and topological structure of their embedding spaces remains poorly understood. In this work, we introduce a comprehensive framework for evaluating LLM embeddings through six complementary metrics that characterize hierarchy, geometry, and topology. Specifically, $δ$-hyperbolicity and ultrametricity quantify the degree of tree-like structure, while Neighbor Joining evaluates how well pairwise distances support hierarchical reconstruction. The Ollivier-Ricci curvature captures local geometric behavior, persistent homology measures multiscale topological stability, and fractal dimension estimates intrinsic complexity. Applying this framework to embeddings from multiple protein LLMs, we reveal how different models encode hierarchical relationships and structural organization. Evaluating the structure of these embeddings in the representation space helps improve geometry-aware model design. This is critical in domains such as bioinformatics and healthcare, where real-world hierarchical and relational structures matter. Our results demonstrate that geometric and topological analysis provides a guiding lens for understanding and potentially improving the representational quality of LLM embeddings.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Chourasia, P., Ali, S., Patterson, M., & Zelikovsky, A. (2025). Uncovering Hierarchical Structure in LLM Embeddings Using Geometric and Topological Measures. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.20926

MLA 9

Chourasia, Prakash, et al. “Uncovering Hierarchical Structure in LLM Embeddings Using Geometric and Topological Measures.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2512.20926.

Chicago

Chourasia, Prakash, Sarwan Ali, Murray Patterson, and Alex Zelikovsky. 2025. “Uncovering Hierarchical Structure in LLM Embeddings Using Geometric and Topological Measures.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.20926.

Harvard

Chourasia, P. et al. (2025) ‘Uncovering Hierarchical Structure in LLM Embeddings Using Geometric and Topological Measures’, arXiv (Cornell University). doi:10.48550/arxiv.2512.20926.

IEEE

P. Chourasia, S. Ali, M. Patterson, and A. Zelikovsky, “Uncovering Hierarchical Structure in LLM Embeddings Using Geometric and Topological Measures,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2512.20926.

BibTeX

@misc{chourasia2025uncovering,
  title     = {{Uncovering Hierarchical Structure in LLM Embeddings Using Geometric and Topological Measures}},
  author    = {Chourasia, Prakash and Ali, Sarwan and Patterson, Murray and Zelikovsky, Alex},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2512.20926},
  url       = {https://doi.org/10.48550/arxiv.2512.20926}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computational Theory and Mathematics › Topological and Geometric Data Analysis

  • large language model embeddings
  • embedding space geometry
  • hierarchy
  • ultrametricity
  • neighbor-joining
  • Ollivier-Ricci curvature
  • persistent homology
  • fractal dimension

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Chourasia, P., Ali, S., Patterson, M., & Zelikovsky, A. (2025). Uncovering Hierarchical Structure in LLM Embeddings Using Geometric and Topological Measures. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2512.20926

How many times has this paper been cited?

0 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Prakash Chourasia, Sarwan Ali, Murray Patterson, Alex Zelikovsky.

What is the DOI of this paper?

10.48550/arxiv.2512.20926, permanently at https://doi.org/10.48550/arxiv.2512.20926. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.