mlsanityData to 14 Oct 2026

BoostTaxo: Zero-Shot Taxonomy Induction via Boosting-Style Agentic Reasoning and Constraint-Aware Calibration

arXiv 2605.12520 ↗First posted 3 Apr 2026cs.CL cs.AIcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

Taxonomy induction is crucial for organizing concepts into explicit and interpretable semantic hierarchies. While existing methods have achieved promising results, their generalization, structural reliability, and efficiency remain limited, hindering their performance in zero-shot and large-scale scenarios. To overcome these limitations, we introduce BoostTaxo, a boosting-style LLM framework for zero-shot taxonomy induction. It takes a set of domain terms as inputs and performs parent identification in a coarse-to-fine manner, employing retrieval-augmented definition refinement, hybrid parent candidate selection, candidate rating, and structure-aware score calibration to improve taxonomy construction. Specifically, a lightweight LLM is used to efficiently filter candidate parents, while a large-scale LLM is employed to rank and score candidate parents for fine-grained parent selection. Structural features are further incorporated to calibrate candidate edge weights and enhance the reliability of the induced taxonomy. The unified BoostTaxo is evaluated on three public benchmark datasets, namely WordNet, DBLP, and SemEval-Sci, and achieves superior or comparable performance to state-of-the-art methods in zero-shot taxonomy induction. The ablation study validates the contribution of the hybrid parent candidate selection and the structure-aware score calibration to the overall performance. Further analysis investigates the impact of candidate selection size on taxonomy quality and presents representative case and failure studies, providing deeper insights into the effectiveness and limitations of the proposed framework.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 27 of its 58 references that are in the map. First posted on arXiv 3 Apr 2026.

Builds on

27 of 58 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQA27 May
  2. 2024GenRES: Rethinking Evaluation for Generative Relation Extraction in the Era of Large Language Models16 Feb

Other references · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  4. 2022Emergent Abilities of Large Language Modelscited by 2,512
  5. 2022PAL: Program-aided Language Modelscited by 652
  6. 2024TinyLlama: An Open-Source Small Language Modelcited by 618
  7. 2022Unified Structure Generation for Universal Information Extractioncited by 221
  8. 2021GPT3Mix: Leveraging Large-scale Language Models for Text Augmentationcited by 187
  9. 2023Large Language Models for Generative Information Extraction: A Surveycited by 185
  10. 2023Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Lawscited by 159
  11. 2019Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddingscited by 49
  12. 2023Enhancing Knowledge Graph Construction Using Large Language Modelscited by 44
13 more
  1. 2023Instruct and Extract: Instruction Tuning for On-Demand Information Extractioncited by 36
  2. 2023Large Language Models Are Zero-Shot Text Classifierscited by 35
  3. 2019HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansioncited by 31
  4. 2023How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?cited by 30
  5. 2025Towards Reasoning Ability of Small Language Modelscited by 29
  6. 2016Improving Hypernymy Detection with an Integrated Path-based and Distributional Methodcited by 27
  7. 2019SetExpan: Corpus-Based Set Expansion via Context Feature Selection and Rank Ensemblecited by 25
  8. 2024Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examplescited by 24
  9. 2024ADELIE: Aligning Large Language Models on Information Extractioncited by 24
  10. 2023Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Constructioncited by 18
  11. 2018End-to-End Reinforcement Learning for Automatic Taxonomy Inductioncited by 17
  12. 2022Distilling Hypernymy Relations from Language Models: On the Effectiveness of Zero-Shot Taxonomy Inductioncited by 8
  13. 2023Learning Semantic Text Similarity to rank Hypernyms of Financial Termscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Heterogeneous LLM Methods for Ontology Learning (Few-Shot Prompting, Ensemble Typing, and Attention-Based Taxonomies)
  2. 2025TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora
  3. 2025Transforming Expert Knowledge into Scalable Ontology via Large Language Models
  4. 2026Curate-Train-Refine: A Closed-Loop Agentic Framework for Zero Shot Classification
  5. 2024FLAME: Self-Supervised Low-Resource Taxonomy Expansion using Large Language Models
  6. 2026From Plausible Hierarchies to Useful Taxonomies: Evaluating Agentic Harnesses on Customer Feedback
  7. 2024Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-shot Hierarchical Text Classification
  8. 2026TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation