Conference paper · 2025 · Open access
Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring
International Conference on Knowledge Capture, 123–130 · Published 9 December 2025 · DOI 10.1145/3731443.3771357
In brief
“Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring” is a 2025 conference paper by Melika Ayoughi and 2 co-authors, published in International Conference on Knowledge Capture. OpenAlex counts 1 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at International Conference on Knowledge Capture.
- Citations
- 1
- Most cited in
- 2026 (1)
- Field-weighted impact
- 0.21
- References
- 77
- Authors
- 3
Abstract
Hyperbolic geometry is an effective geometry for embedding hierarchical data structures. Hyperbolic learning has therefore become increasingly prominent in machine learning applications where data is hierarchically organized or governed by hierarchical semantics, ranging from recommendation systems to computer vision. The quality of hyperbolic embeddings is tightly coupled to the structure of the input hierarchy, which is often derived from knowledge graphs or ontologies. Recent work has uncovered that for an optimal hyperbolic embedding, a high branching factor and single inheritance are key, while embedding algorithms are robust to imbalance and hierarchy size. To assist knowledge engineers in reorganizing hierarchical knowledge, this paper investigates whether Large Language Models (LLMs) have the ability to automatically restructure hierarchies to meet these criteria. We propose a prompt-based approach to transform existing hierarchies using LLMs, guided by known desiderata for hyperbolic embeddings. Experiments on 16 diverse hierarchies show that LLM-restructured hierarchies consistently yield higher-quality hyperbolic embeddings across several standard embedding quality metrics. Moreover, we show how LLM-guided hierarchy restructuring enables explainable reorganizations, providing justifications to knowledge engineers.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Ayoughi, M., Mettes, P., & Groth, P. (2025). Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring. International Conference on Knowledge Capture, 123–130. https://doi.org/10.1145/3731443.3771357
MLA 9
Ayoughi, Melika, et al. “Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring.” International Conference on Knowledge Capture, 2025, pp. 123–130. https://doi.org/10.1145/3731443.3771357.
Chicago
Ayoughi, Melika, Pascal Mettes, and Paul Groth. 2025. “Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring.” International Conference on Knowledge Capture: 123–130. https://doi.org/10.1145/3731443.3771357.
Harvard
Ayoughi, M., Mettes, P. and Groth, P. (2025) ‘Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring’, International Conference on Knowledge Capture, pp. 123–130. doi:10.1145/3731443.3771357.
IEEE
M. Ayoughi, P. Mettes, and P. Groth, “Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring,” International Conference on Knowledge Capture, pp. 123–130, 2025, doi: 10.1145/3731443.3771357.
BibTeX
@inproceedings{ayoughi2025minimizing,
title = {{Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring}},
author = {Ayoughi, Melika and Mettes, Pascal and Groth, Paul},
booktitle = {International Conference on Knowledge Capture},
year = {2025},
pages = {123--130},
doi = {10.1145/3731443.3771357},
url = {https://doi.org/10.1145/3731443.3771357}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- hyperbolic embeddings
- large language models
- knowledge graphs
- ontology (information science)
- hierarchical data
- embedding distortion
- branching factor
- inheritance (object-oriented programming)
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Ayoughi, M., Mettes, P., & Groth, P. (2025). Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring. International Conference on Knowledge Capture, 123–130. https://doi.org/10.1145/3731443.3771357
How many times has this paper been cited?
1 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 International Conference on Knowledge Capture: sign in and open the full text from this page.
Who wrote this paper?
Melika Ayoughi, Pascal Mettes, Paul Groth.
What is the DOI of this paper?
10.1145/3731443.3771357, permanently at https://doi.org/10.1145/3731443.3771357. 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.