# TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora

arXiv: https://arxiv.org/abs/2506.10737 · HTML: https://mlsanity.com/paper/2506.10737/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 12 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [Growth rates of modern science: A latent piecewise growth curve approach to model publication numbers from established and new literature databases](https://mlsanity.com/paper/2012.07675/) (2020)
- [Large Language Models Enable Few-Shot Clustering](https://mlsanity.com/paper/2307.00524/) (2023)
- [TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering](https://mlsanity.com/paper/1812.09551/) (2018)
- [HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion](https://mlsanity.com/paper/1910.08194/) (2019)
- [TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters](https://mlsanity.com/paper/2201.06771/) (2022)
- [Pushing The Limit of LLM Capacity for Text Classification](https://mlsanity.com/paper/2402.07470/) (2024)
- [TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision](https://mlsanity.com/paper/2403.00165/) (2024)
- [Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples](https://mlsanity.com/paper/2402.07386/) (2024)
- [CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring](https://mlsanity.com/paper/2010.06714/) (2020)
- [Are Large Language Models a Good Replacement of Taxonomies?](https://mlsanity.com/paper/2406.11131/) (2024)
- [Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Construction](https://mlsanity.com/paper/2309.01715/) (2023)
- [Taxonomy-guided Semantic Indexing for Academic Paper Search](https://mlsanity.com/paper/2410.19218/) (2024)
- [A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion](https://mlsanity.com/paper/2402.13405/) (2024)
- [Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generation](https://mlsanity.com/paper/2211.01981/) (2022)
- [Creating a Fine Grained Entity Type Taxonomy Using LLMs](https://mlsanity.com/paper/2402.12557/) (2024)
- [Self-supervised Topic Taxonomy Discovery in the Box Embedding Space](https://mlsanity.com/paper/2408.15050/) (2024)
- [Quantifying the rise and fall of scientific fields](https://mlsanity.com/paper/2107.03749/) (2021)

## Built on by (most cited first, 23 of 23)

- [Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering](https://mlsanity.com/paper/2509.19125/) (2025)
- [Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration](https://mlsanity.com/paper/2603.12226/) (2026)
- [Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration](https://mlsanity.com/paper/2509.15786/) (2025)
- [ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment](https://mlsanity.com/paper/2606.00644/) (2026)
- [CHisAgent: A Multi-Agent Framework for Event Taxonomy Construction in Ancient Chinese Cultural Systems](https://mlsanity.com/paper/2601.05520/) (2026)
- [EvoTaxo: Building and Evolving Taxonomy from Social Media Streams](https://mlsanity.com/paper/2603.19711/) (2026)
- [Agentic generation of verifiable rules for deterministic, self-expanding reaction classification](https://mlsanity.com/paper/2607.01061/) (2026)
- [SCALE: Scientific Concept Aggregation via LLMs and Embeddings for Fine-Grained Taxonomy Extension](https://mlsanity.com/paper/2608.07254/) (2026)
- [MVSS: A Unified Framework for Multi-View Structured Survey Generation](https://mlsanity.com/paper/2601.09504/) (2026)
- [AI Assisted Economics Measurement From Survey: Evidence from Public Employee Pension Choice](https://mlsanity.com/paper/2602.02604/) (2026)
- [PROMPT2BOX:Improving LLM Weakness Discovery and Specificity Estimation by Uncovering Entailment Structure among Prompts](https://mlsanity.com/paper/2603.21438/) (2026)
- [SC-Taxo: Hierarchical Taxonomy Generation under Semantic Consistency Constraints using Large Language Models](https://mlsanity.com/paper/2605.00620/) (2026)
- [Building a Custom Taxonomy of AI Skills and Tasks from the Ground Up with Job Postings](https://mlsanity.com/paper/2605.21029/) (2026)
- [Indexing the Unreadable: LLM-Native Recursive Construction and Search of Service Taxonomies](https://mlsanity.com/paper/2605.29270/) (2026)
- [ATLAS: Agentic Taxonomy of Large-Scale Software Ecosystems](https://mlsanity.com/paper/2606.21597/) (2026)
- [CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph](https://mlsanity.com/paper/2606.30175/) (2026)
- [PaperRouter-Agent: A Content-Grounded LLM Agent for Personalized Hierarchical Paper Routing](https://mlsanity.com/paper/2607.11564/) (2026)
- [An Agentic Hybrid Top-Down and Bottom-Up Approach to Knowledge Graph Generation](https://mlsanity.com/paper/2608.07023/) (2026)
- [Security and Privacy Taxonomy Generation from Mobile App Reviews](https://mlsanity.com/paper/2608.09049/) (2026)
- [Autoresearch for Marketplace Catalogs: From Legacy Forms to AI-Native Matching](https://mlsanity.com/paper/2609.00274/) (2026)
- [SPARROW: Scalable Taxonomy Induction via Structure-Preserving Partitioning and Constraint-Guided Merging](https://mlsanity.com/paper/2609.07307/) (2026)
- [Towards Automatic Evolution Tree Generation from Citation Graphs](https://mlsanity.com/paper/2609.09561/) (2026)
- [Generated Query Expansion Still Helps Strong Sparse Retrieval: A Controlled Study with SPLADE-v3](https://mlsanity.com/paper/2609.37911/) (2026)

## Abstract (arXiv)

The rapid evolution of scientific fields introduces challenges in organizing and retrieving scientific literature. While expert-curated taxonomies have traditionally addressed this need, the process is time-consuming and expensive. Furthermore, recent automatic taxonomy construction methods either (1) over-rely on a specific corpus, sacrificing generalizability, or (2) depend heavily on the general knowledge of large language models (LLMs) contained within their pre-training datasets, often overlooking the dynamic nature of evolving scientific domains. Additionally, these approaches fail to account for the multi-faceted nature of scientific literature, where a single research paper may contribute to multiple dimensions (e.g., methodology, new tasks, evaluation metrics, benchmarks). To address these gaps, we propose TaxoAdapt, a framework that dynamically adapts an LLM-generated taxonomy to a given corpus across multiple dimensions. TaxoAdapt performs iterative hierarchical classification, expanding both the taxonomy width and depth based on corpus' topical distribution. We demonstrate its state-of-the-art performance across a diverse set of computer science conferences over the years to showcase its ability to structure and capture the evolution of scientific fields. As a multidimensional method, TaxoAdapt generates taxonomies that are 26.51% more granularity-preserving and 50.41% more coherent than the most competitive baselines judged by LLMs.