#Taxonomies#Large Language Models#Taxoria#Knowledge Retrieval#Information Structuring#ECAI 2025#Taxonomy Enrichment
📌 Key Takeaways
Taxoria uses existing taxonomies as seeds rather than extracting internal LLM taxonomies
The pipeline prompts LLMs to propose candidate nodes for taxonomy enhancement
Validation mechanisms prevent hallucinations and ensure semantic relevance
The final output includes provenance tracking and visualization capabilities
📖 Full Retelling
Researchers Zeinab Ghamlouch and Mehwish Alam introduced Taxoria, a novel taxonomy enrichment pipeline that leverages Large Language Models to enhance existing taxonomies, in a paper published on arXiv on November 21, 2025, and presented at the ECAI 2025 Demo Track, addressing the critical issue of limited coverage and outdated nodes in current taxonomies that reduce their effectiveness in knowledge retrieval. Unlike previous approaches that extract internal taxonomies from LLMs, Taxoria takes a different path by using an existing taxonomy as a seed and prompts an LLM to propose candidate nodes for enrichment, creating a more controlled and targeted enhancement process. The researchers developed a validation mechanism to mitigate the risk of hallucinations and ensure semantic relevance before integrating new nodes into the taxonomy structure, addressing one of the major challenges when working with generative AI systems. The final output of the Taxoria pipeline includes not only an enriched taxonomy but also provenance tracking capabilities and visualization tools for analyzing the final merged taxonomy, providing researchers and practitioners with both enhanced knowledge organization systems and insights into the enrichment process.
🏷️ Themes
Artificial Intelligence, Information Retrieval, Knowledge Organization
Taxonomy is a practice and science concerned with classification or categorization. Typically, there are two parts to it: the development of an underlying scheme of classes (a taxonomy) and the allocation of things to the classes (classification).
Originally, taxonomy referred only to the classifica...
A large language model (LLM) is a language model trained with self-supervised machine learning on a vast amount of text, designed for natural language processing tasks, especially language generation. The largest and most capable LLMs are generative pre-trained transformers (GPTs) that provide the c...
No entity connections available yet for this article.
Original Source
--> Computer Science > Information Retrieval arXiv:2602.22213 [Submitted on 21 Nov 2025] Title: Enriching Taxonomies Using Large Language Models Authors: Zeinab Ghamlouch , Mehwish Alam View a PDF of the paper titled Enriching Taxonomies Using Large Language Models, by Zeinab Ghamlouch and 1 other authors View PDF HTML Abstract: Taxonomies play a vital role in structuring and categorizing information across domains. However, many existing taxonomies suffer from limited coverage and outdated or ambiguous nodes, reducing their effectiveness in knowledge retrieval. To address this, we present Taxoria, a novel taxonomy enrichment pipeline that leverages Large Language Models to enhance a given taxonomy. Unlike approaches that extract internal LLM taxonomies, Taxoria uses an existing taxonomy as a seed and prompts an LLM to propose candidate nodes for enrichment. These candidates are then validated to mitigate hallucinations and ensure semantic relevance before integration. The final output includes an enriched taxonomy with provenance tracking and visualization of the final merged taxonomy for analysis. Comments: Published in ECAI 2025 Demo Track Subjects: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2602.22213 [cs.IR] (or arXiv:2602.22213v1 [cs.IR] for this version) https://doi.org/10.48550/arXiv.2602.22213 Focus to learn more arXiv-issued DOI via DataCite Journal reference: FAIA 2025 5147-5150 (2025) Related DOI : https://doi.org/10.3233/FAIA251441 Focus to learn more DOI linking to related resources Submission history From: Zeinab Ghamlouch [ view email ] [v1] Fri, 21 Nov 2025 10:25:59 UTC (272 KB) Full-text links: Access Paper: View a PDF of the paper titled Enriching Taxonomies Using Large Language Models, by Zeinab Ghamlouch and 1 other authors View PDF HTML TeX Source view license Current browse context: cs.IR < prev | next > new | recent | 2026-02 Change to browse by: cs cs.AI cs.CL References &...
