# Building a Custom Taxonomy of AI Skills and Tasks from the Ground Up with Job Postings

arXiv: https://arxiv.org/abs/2605.21029 · HTML: https://mlsanity.com/paper/2605.21029/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 69 references that are in the map.
- First posted on arXiv 20 May 2026.

## Builds on (most cited first, 10 of 10)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [EmbeddingGemma: Powerful and Lightweight Text Representations](https://mlsanity.com/paper/2509.20354/) (2025)
- [TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering](https://mlsanity.com/paper/1812.09551/) (2018)
- [Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples](https://mlsanity.com/paper/2402.07386/) (2024)
- [TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora](https://mlsanity.com/paper/2506.10737/) (2025)
- [End-to-End Reinforcement Learning for Automatic Taxonomy Induction](https://mlsanity.com/paper/1805.04044/) (2018)
- [Text Clustering as Classification with LLMs](https://mlsanity.com/paper/2410.00927/) (2024)
- [Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering](https://mlsanity.com/paper/2509.19125/) (2025)
- [An Improved Method for Class-specific Keyword Extraction: A Case Study in the German Business Registry](https://mlsanity.com/paper/2407.14085/) (2024)

## Abstract (arXiv)

Utilizing LLMs for automated taxonomy construction presents a clear opportunity for the comprehensive, yet efficient mapping of potentially complex domains. When contending with high volumes of rapidly growing corpora, however, it becomes unclear how to best leverage such data for optimal taxonomy construction. Taking the case of systematizing AI skills in the workplace, we use two large-scale job postings corpora to investigate key design decisions for the inclusion (or exclusion) of data points for taxonomy construction. We propose TaxonomyBuilder as a blueprint for our systematic study, with which we evaluate various configurations of custom, data-informed, and hierarchical taxonomies. We demonstrate that less data can provide more clarity: filtering inputs to TaxonomyBuilder provides better domain-specific coverage than offering unfiltered inputs to clustering and LLM-enhanced hierarchical taxonomy labeling tools.