mlsanityData to 14 Oct 2026

Multi-Hop Reasoning for Question Answering with Hyperbolic Representations

arXiv 2507.03612 ↗First posted 4 Jul 2025cs.CL cs.AIcited by 1

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Hyperbolic representations are effective in modeling knowledge graph data which is prevalently used to facilitate multi-hop reasoning. However, a rigorous and detailed comparison of the two spaces for this task is lacking. In this paper, through a simple integration of hyperbolic representations with an encoder-decoder model, we perform a controlled and comprehensive set of experiments to compare the capacity of hyperbolic space versus Euclidean space in multi-hop reasoning. Our results show that the former consistently outperforms the latter across a diverse set of datasets. In addition, through an ablation study, we show that a learnable curvature initialized with the delta hyperbolicity of the utilized data yields superior results to random initializations. Furthermore, our findings suggest that hyperbolic representations can be significantly more advantageous when the datasets exhibit a more hierarchical structure.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 28 of its 38 references that are in the map. First posted on arXiv 4 Jul 2025.

Builds on

28 of 38 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answering9 Oct

Other references · 27

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  4. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  5. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  6. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 905
  7. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
  8. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 684
  9. 2018Hyperbolic Neural Networkscited by 402
  10. 2019Hyperbolic Graph Convolutional Neural Networkscited by 402
  11. 2018Generating Wikipedia by Summarizing Long Sequencescited by 335
  12. 2019Hyperbolic Image Embeddingscited by 221
15 more
  1. 2020Low-Dimensional Hyperbolic Knowledge Graph Embeddingscited by 195
  2. 2019Multi-relational Poincar'e Graph Embeddingscited by 126
  3. 2020Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answeringcited by 122
  4. 2022Hyperbolic Vision Transformers: Combining Improvements in Metric Learningcited by 111
  5. 2018Multi-Hop Knowledge Graph Reasoning with Reward Shapingcited by 102
  6. 2018Embedding Text in Hyperbolic Spacescited by 76
  7. 2024Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answeringcited by 51
  8. 2018An Interpretable Reasoning Network for Multi-Relation Question Answeringcited by 47
  9. 2023End-to-End Beam Retrieval for Multi-Hop Question Answeringcited by 35
  10. 2019HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completioncited by 20
  11. 2024Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answeringcited by 20
  12. 2021Exploiting Reasoning Chains for Multi-hop Science Question Answeringcited by 15
  13. 2022HyperMiner: Topic Taxonomy Mining with Hyperbolic Embeddingcited by 15
  14. 2024Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answeringcited by 14
  15. 2021Hyperbolic Temporal Knowledge Graph Embeddings with Relational and Time Curvaturescited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Intrinsic Lorentz Neural Networkcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2025Fully Geometric Multi-Hop Reasoning on Knowledge Graphs with Transitive Relations
  2. 2024Efficient Parallel Multi-Hop Reasoning: A Scalable Approach for Knowledge Graph Analysis
  3. 2025KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration
  4. 2025Encoder-Free Knowledge-Graph Reasoning with LLMs via Hyperdimensional Path Retrieval
  5. 2022Hypergraph Transformer: Weakly-supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering
  6. 2025StepChain GraphRAG: Reasoning Over Knowledge Graphs for Multi-Hop Question Answering
  7. 2026HyperProve: Answer-Guided Hypergraph Expansion for Multi-Hop Question Answering
  8. 2024Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs