# Taxonomy Inference for Tabular Data Using Large Language Models

arXiv: https://arxiv.org/abs/2503.21810 · HTML: https://mlsanity.com/paper/2503.21810/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 57 references that are in the map.
- First posted on arXiv 25 Mar 2025.

## Builds on (most cited first, 21 of 21)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Semantics-aware Dataset Discovery from Data Lakes with Contextualized Column-based Representation Learning](https://mlsanity.com/paper/2210.01922/) (2022)
- [Contextual Semantic Embeddings for Ontology Subsumption Prediction](https://mlsanity.com/paper/2202.09791/) (2022)
- [CHORUS: Foundation Models for Unified Data Discovery and Exploration](https://mlsanity.com/paper/2306.09610/) (2023)
- [Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples](https://mlsanity.com/paper/2402.07386/) (2024)
- [Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data](https://mlsanity.com/paper/2402.12869/) (2024)
- [Efficient Joinable Table Discovery in Data Lakes: A High-Dimensional Similarity-Based Approach](https://mlsanity.com/paper/2010.13273/) (2020)
- [Towards Ontology Construction with Language Models](https://mlsanity.com/paper/2309.09898/) (2023)
- [Fine-grained Entity Typing via Label Reasoning](https://mlsanity.com/paper/2109.05744/) (2021)
- [Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Construction](https://mlsanity.com/paper/2309.01715/) (2023)
- [DeepJoin: Joinable Table Discovery with Pre-trained Language Models](https://mlsanity.com/paper/2212.07588/) (2022)
- [End-to-End Ontology Learning with Large Language Models](https://mlsanity.com/paper/2410.23584/) (2024)
- [MZET: Memory Augmented Zero-Shot Fine-grained Named Entity Typing](https://mlsanity.com/paper/2004.01267/) (2020)
- [RaTE: a Reproducible automatic Taxonomy Evaluation by Filling the Gap](https://mlsanity.com/paper/2307.09706/) (2023)
- [Surprisingly Fragile: Assessing and Addressing Prompt Instability in Multimodal Foundation Models](https://mlsanity.com/paper/2408.14595/) (2024)

## Built on by (most cited first, 2 of 2)

- [Conceptual Schema Inference for Tabular Datasets using Large Language Models](https://mlsanity.com/paper/2509.04632/) (2025)
- [Single and Multi Truth Data Fusion using Large Language Models](https://mlsanity.com/paper/2606.28062/) (2026)

## Abstract (arXiv)

Taxonomy inference for tabular data is a critical task of schema inference, aiming at discovering entity types (i.e., concepts) of the tables and building their hierarchy. It can play an important role in data management, data exploration, ontology learning, and many data-centric applications. Existing schema inference systems focus more on XML, JSON or RDF data, and often rely on lexical formats and structures of the data for calculating similarities, with limited exploitation of the semantics of the text across a table. Motivated by recent works on taxonomy completion and construction using Large Language Models (LLMs), this paper presents two LLM-based methods for taxonomy inference for tables: (i) EmTT which embeds columns by fine-tuning with contrastive learning encoder-alone LLMs like BERT and utilises clustering for hierarchy construction, and (ii) GeTT which generates table entity types and their hierarchy by iterative prompting using a decoder-alone LLM like GPT-4. Extensive evaluation on three real-world datasets with six metrics covering different aspects of the output taxonomies has demonstrated that EmTT and GeTT can both produce taxonomies with strong consistency relative to the Ground Truth.