---
title: "Ontology-Aware LLMs for Human-Usable Knowledge Graph Systems"
authors:
  - "Luiz do Valle Miranda"
doi: "10.24963/ijcai.2026/941"
url: "https://ijcai.org/proceedings/2026/941"
pdf: "https://ijcai.org/proceedings/2026/0941.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "8325-8326"
track: "Doctoral Consortium"
keywords:
  - "Humans and AI: Intelligent user interfaces"
  - "Knowledge Representation and Reasoning: Semantic Web"
  - "Natural Language Processing: Language models"
---

# Ontology-Aware LLMs for Human-Usable Knowledge Graph Systems

Luiz do Valle Miranda

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 8325-8326. DOI: [10.24963/ijcai.2026/941](https://doi.org/10.24963/ijcai.2026/941)

## Abstract

Knowledge graphs (KGs) promise machine-readable semantics together with human-readable labels and relations, yet domain experts struggle to use them due to technical barriers, especially in automatically constructed graphs with unlabeled nodes and complex connections. While LLMs enable KG interfaces such as retrieval-augmented generation, their potential to leverage ontology definitions to improve graph readability remains unexplored. This research investigates LLMs as ontology-aware verbalization interfaces that generate human-readable and usable textual information encoded in the KG structure.