# ReLTEx: Reliable LLM-based Taxonomy Expansion

arXiv: https://arxiv.org/abs/2608.10970 · HTML: https://mlsanity.com/paper/2608.10970/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Builds on (most cited first, 7 of 7)

- [YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomy](https://mlsanity.com/paper/2308.11884/) (2023)
- [STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths](https://mlsanity.com/paper/2006.10217/) (2020)
- [Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples](https://mlsanity.com/paper/2402.07386/) (2024)
- [Are Large Language Models a Good Replacement of Taxonomies?](https://mlsanity.com/paper/2406.11131/) (2024)
- [LITE: LLM-Impelled efficient Taxonomy Evaluation](https://mlsanity.com/paper/2504.01369/) (2025)
- [FUSE: Measure-Theoretic Compact Fuzzy Set Representation for Taxonomy Expansion](https://mlsanity.com/paper/2506.08409/) (2025)
- [Enriching Taxonomies Using Large Language Models](https://mlsanity.com/paper/2602.22213/) (2025)

## Abstract (arXiv)

Recent advances in Large Language Models (LLMs) have demonstrated strong capabilities in generating semantically relevant concepts and relations, making them promising tools for taxonomy enrichment. However, directly relying on LLM-generated expansions often leads to noisy, redundant, or hierarchically inconsistent structures, limiting their reliability for automated taxonomy expansion. In this paper, we present ReLTEx, a framework for reliable LLM-based taxonomy expansion. ReLTEx combines LLM-driven candidate generation with structure-aware validation and recursive expansion control to improve the consistency and quality of generated taxonomies by reducing hallucinations. We evaluate the proposed framework using benchmark taxonomies under a masked taxonomy expansion setting and compare multiple validation strategies. Experimental results, supported by both adapted evaluation metrics and human evaluation, demonstrate that ReLTEx produces more reliable and semantically coherent taxonomy expansions.