# Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring

arXiv: https://arxiv.org/abs/2511.20679 · HTML: https://mlsanity.com/paper/2511.20679/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 79 references that are in the map.
- First posted on arXiv 16 Nov 2025.

## Builds on (most cited first, 30 of 31)

- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Poincar'e Embeddings for Learning Hierarchical Representations](https://mlsanity.com/paper/1705.08039/) (2017)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry](https://mlsanity.com/paper/1806.03417/) (2018)
- [Representation Tradeoffs for Hyperbolic Embeddings](https://mlsanity.com/paper/1804.03329/) (2018)
- [Hyperbolic Entailment Cones for Learning Hierarchical Embeddings](https://mlsanity.com/paper/1804.01882/) (2018)
- [Hyperbolic Deep Neural Networks: A Survey](https://mlsanity.com/paper/2101.04562/) (2021)
- [Hyperbolic Image-Text Representations](https://mlsanity.com/paper/2304.09172/) (2023)
- [LLMs4OL: Large Language Models for Ontology Learning](https://mlsanity.com/paper/2307.16648/) (2023)
- [Embedding Text in Hyperbolic Spaces](https://mlsanity.com/paper/1806.04313/) (2018)
- [Hyperbolic Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/2305.06611/) (2023)
- [Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases](https://mlsanity.com/paper/2009.11564/) (2020)
- [Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings](https://mlsanity.com/paper/1902.00913/) (2019)
- [Hierarchical Image Classification using Entailment Cone Embeddings](https://mlsanity.com/paper/2004.03459/) (2020)
- [EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding](https://mlsanity.com/paper/2309.08816/) (2023)
- [OLaLa: Ontology Matching with Large Language Models](https://mlsanity.com/paper/2311.03837/) (2023)
- [OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learning](https://mlsanity.com/paper/1911.06487/) (2019)
- [HICF: Hyperbolic Informative Collaborative Filtering](https://mlsanity.com/paper/2207.09051/) (2022)
- [HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion](https://mlsanity.com/paper/1908.04895/) (2019)
- [BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity](https://mlsanity.com/paper/2406.17720/) (2024)
- [Skin Lesion Recognition with Class-Hierarchy Regularized Hyperbolic Embeddings](https://mlsanity.com/paper/2209.05842/) (2022)
- [Curved Geometric Networks for Visual Anomaly Recognition](https://mlsanity.com/paper/2208.01188/) (2022)
- [Construction of Knowledge Graphs: State and Challenges](https://mlsanity.com/paper/2302.11509/) (2023)
- [Accelerating Knowledge Graph and Ontology Engineering with Large Language Models](https://mlsanity.com/paper/2411.09601/) (2024)
- [Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space](https://mlsanity.com/paper/2502.17130/) (2025)
- [Refining Wikidata Taxonomy using Large Language Models](https://mlsanity.com/paper/2409.04056/) (2024)
- [Hierarchical Material Recognition from Local Appearance](https://mlsanity.com/paper/2505.22911/) (2025)
- [Find Parent then Label Children: A Two-stage Taxonomy Completion Method with Pre-trained Language Model](https://mlsanity.com/paper/2406.17739/) (2024)

## Built on by (most cited first, 1 of 1)

- [SC-Taxo: Hierarchical Taxonomy Generation under Semantic Consistency Constraints using Large Language Models](https://mlsanity.com/paper/2605.00620/) (2026)

## Abstract (arXiv)

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.