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

Yancheng Ling, Zhenlin Qin, Leizhen Wang, Zhenliang Ma

arXiv:2605.12520 · 2026-05-14 공개 · arXiv · PDF

retrieval-augmented zero-shot structure-aware candidate-selection wordnet dblp semeval-sci boosting-style

Abstract

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.

한국어 요약

📋 한 줄 요약

**[지식 그래프 / 분류 체계]** LLM 부스팅 스타일 추론과 구조 인지 캘리브레이션을 결합한 zero-shot 분류 체계 자동 구축 프레임워크 BoostTaxo 제안.

🎯 핵심 기여도

💡 핵심 아이디어

분류 체계 유도는 단순 LLM 분류가 아니라 **coarse-to-fine boosting**으로 다뤄야 한다. 경량/대형 LLM의 역할 분담과 구조 인지 캘리브레이션을 통해 비용·구조 신뢰성·일반화를 동시에 향상시킬 수 있다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: zero-shot taxonomy induction이 LLM 자원을 효율적으로 분할 사용하면서도 구조적으로 신뢰할 만한 결과를 낼 수 있음을 보여준 사례. **한계**: 평가가 세 공개 벤치마크에 한정되며, 매우 큰 멀티도메인 산업 분류 체계에서의 확장성은 추가 검증 필요.

🚀 실용적 활용