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

Yancheng Ling; Zhenlin Qin; Leizhen Wang; Zhenliang Ma

cs.CLApr 3, 2026

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

Authors: Yancheng Ling, Zhenlin Qin, Leizhen Wang, Zhenliang Ma

Organizations: KTH Royal Institute of Technology, 11428 Sweden · Monash University, Clayton, Australia, 3800

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.

Figures & tables

Fig. 1: Boosting-Style Zero-Shot Taxonomy Induction with Large Language Models

Fig. 2: The boosting-style zero-shot framework for taxonomy induction. Starting from a root concept and a term set, the framework first enriches term semantics through retrieval-augmented definitions, which combine Wikipedia retrieval with definition refinement. Then, for each term, it performs parent candidate selection in three stages. First, Hybrid Parent Candidate Selection identifies a set of potential parents by jointly considering Is-A judgment and definition matching. Second, Candidate Ranking and Scoring ranks these candidates and assigns an initial score to each of them. Third, Calibration with Structural Features further adjusts these scores to improve their structural consistency and reliability. After obtaining parent candidates and calibrated scores for all terms, the final taxonomy is constructed by applying a maximum spanning arborescence algorithm.

Fig. 3: Prompt design for LLM-Based term definition refinement

Fig. 4: Prompt design for LLM-based candidate parent ranking and scoring

Fig. 5: Prompt design for LLM-Based calibration of candidate parent scores

Input: Candidate edges

E

, root node

r

, threshold

\tau_{m}

, LLM

Output: Adjusted candidate edges

E^{\prime}

1. Filter mutual edges in

E

with threshold

\tau_{m}

to obtain the filtered edge set

E_{f}

2. Normalize the scores of edges in

E_{f}

to obtain

s(t,p)\in[0,1]

3. Build candidate mappings

P(t)

and the parent-to-children graph from

E_{f}

4. For each edge

(t,p)\in E_{f}

, compute

\mathrm{margin}(t,p)

\mathrm{pop}(p)

\mathrm{pb}(t,p)

\mathrm{skip\_support}(t,p)

\mathrm{coh}(t,p)

, and

\mathrm{depth\_pen}(p)

5. For each child term

t

, query the LLM with all candidate parents in

P(t)

and obtain

\mathrm{penalty}_{\mathrm{eff}}(t,p)\in[0,0.5]

for each

p\in P(t)

TABLE I: LLM-based score calibration algorithm

Model	WordNet						DBLP						SemEval-Sci
Model	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$
Supervised Fine-tuning
Graph2Taxo	79.20	47.80	59.60	75.60	37.00	49.70	47.85	30.23	37.05	46.63	28.49	35.37	82.45	36.15	50.27	79.37	34.52	46.87
CTP	69.30	66.20	66.70	53.30	49.80	51.50	45.62	41.39	43.40	38.21	33.73	35.83	52.41	33.88	41.16	31.18	29.42	30.27
CTP-Llama-2-7B	73.48	70.02	71.71	55.42	51.98	53.64	48.73	39.88	43.86	44.39	35.81	39.64	61.98	54.09	57.77	48.33	41.92	44.90
5-shot Setting

TABLE II: Performance comparison on WordNet, DBLP, and SemEval-Sci datasets.

Setting	WordNet						DBLP						SemEval-Sci
Setting	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$
w/o HPCS	71.60	82.06	76.47	57.38	57.28	57.33	34.27	84.74	48.80	45.66	45.66	45.66	90.28	60.41	72.39	54.08	53.98	54.03
w/ HPCS	79.00	80.65	79.81	61.21	61.19	61.20	39.55	85.41	54.07	43.21	43.21	43.21	93.88	65.76	77.34	57.88	57.88	57.88

TABLE III: Ablation study on the effect of Hybrid Parent Candidate Selection across WordNet, DBLP, and SemEval-Sci datasets.

Setting	WordNet						DBLP						SemEval-Sci
Setting	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$
w/o LSC-SF	79.00	80.65	79.81	61.21	61.19	61.20	39.55	85.41	54.07	43.21	43.21	43.21	93.88	65.76	77.34	57.88	57.88	57.88
w/ LSC-SF	84.29	81.34	82.79	63.57	63.43	63.50	59.02	80.81	68.21	48.55	48.55	48.55	88.11	70.60	78.39	60.88	60.88	60.88

TABLE IV: Ablation study on the effect of LLM-based Score Calibration with Structural Features across WordNet, DBLP, and SemEval-Sci datasets.

Setting	WordNet						DBLP						SemEval-Sci
Setting	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$
$top_{k2}=1$	82.55	82.75	82.65	63.71	63.66	63.69	59.86	76.66	67.22	40.53	40.53	40.53	90.59	63.59	74.73	56.64	56.64	56.64
$top_{k2}=3$	79.00	80.65	79.81	61.21	61.19	61.20	39.55	85.41	54.07	43.21	43.21	43.21	93.88	65.76	77.34	57.88	57.88	57.88
$top_{k2}=5$	79.17	79.98	79.57	60.72	60.69	60.71	33.28	85.86	47.96	43.43	43.43	43.43	94.41	63.89	76.21	57.35	57.35	57.35

TABLE V: Ablation study on the choice of

top_{k2}

across WordNet, DBLP, and SemEval-Sci datasets.

Model	WordNet						DBLP						SemEval-Sci
Model	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$	$P_{a}$	$R_{a}$	$F1_{a}$	$P_{e}$	$R_{e}$	$F1_{e}$
Qwen3-14B	85.30	75.04	79.84	55.46	55.21	55.34	51.83	76.21	61.70	39.73	39.64	39.69	85.38	65.36	74.04	53.37	53.27	53.32
Qwen3-30B	77.10	80.27	78.65	55.77	55.62	55.69	53.72	79.46	64.10	46.41	46.10	46.26	76.57	70.85	73.60	57.35	57.35	57.35
GPT-4mini	78.82	70.27	74.30	46.56	46.27	46.42	53.78	78.23	63.74	42.32	42.32	42.32	91.56	63.44	74.95	47.43	47.43	47.43
GPT-4o	84.29	81.34	82.79	63.57	63.43	63.50	59.02	80.81	68.21	48.55	48.55	48.55	88.11	70.60	78.39	60.88	60.88	60.88

TABLE VI: Ablation study results across WordNet, DBLP, and SemEval-Sci datasets using Micro average scores.

Fig. 6: Comparison of taxonomy construction results across different methods.(a) is the ground truth taxonomy, and (b)–(d) show the taxonomies generated by GPT-4o using CoL five-shot, CoL zero-shot, and BoostTaxo zero-shot, respectively. Green indicates correct nodes and edges, while orange indicates incorrect ones. Among the three settings, BoostTaxo zero-shot yields the structure that is closest to the ground truth.

Fig. 7: Representative failure cases in taxonomy construction. In each subfigure, the left side shows the ground-truth taxonomy and the right side shows the predicted taxonomy. Green indicates correct terms and edges, while orange indicates incorrect ones. (a) shows hierarchy flattening, where intermediate levels are removed and descendants are directly attached to higher-level terms. (b) shows excessive hierarchy depth, where extra intermediate terms are incorrectly introduced. (c) shows sibling node confusion, where a term is attached to an incorrect sibling branch. (d) shows cross-branch misattachment, where a term is assigned to the wrong semantic branch.

Taxonomy Induction

See all 16 papers

Sep 7, 2026

SPARROW: Scalable Taxonomy Induction via Structure-Preserving Partitioning and Constraint-Guided Merging

Taxonomy induction aims to organize concept sets into coherent hierarchical structures. Recent LLM-based methods can induce taxonomies directly from flat term lists, avoiding the need for corpora, but degrade sharply as concept sets scale up. We argue that this degradation stems not only from context length limitations, but also from structural failures in hierarchical reasoning. To address this, we adopt a divide-and-merge paradigm that partitions concepts into smaller subsets, induces local taxonomies, and merges them into a global hierarchy. However, we identify two structural failure modes inherent to this paradigm: Structural Fragmentation, where partitioning weakens local hierarchical signals, and Parent Displacement, where locally plausible relations are misplaced in the global hierarchy. To address both, we propose SPARROW, a scalable taxonomy induction framework that combines structure-preserving spectral partitioning to retain hierarchical connectivity within each block, and constraint-guided incremental fusion that treats block-level relations as structural constraints rather than ground truth for global placement. Experiments on large-scale benchmarks show that SPARROW consistently achieves the strongest global structural quality across backbones. The code is available at https://github.com/rebeccazyr/SPARROW.

Yirui Zhang, Yixuan Tang, Yandong Sun +2

School of Computing, National University of Singapore

Spectral Clustering Taxonomy Induction

Ask PDF

Aug 11, 2026

ReLTEx: Reliable LLM-based Taxonomy Expansion

Recent advances in Large Language Models (LLMs) have demonstrated strong capabilities in generating semantically relevant concepts and relations, making them promising tools for taxonomy enrichment. However, directly relying on LLM-generated expansions often leads to noisy, redundant, or hierarchically inconsistent structures, limiting their reliability for automated taxonomy expansion. In this paper, we present ReLTEx, a framework for reliable LLM-based taxonomy expansion. ReLTEx combines LLM-driven candidate generation with structure-aware validation and recursive expansion control to improve the consistency and quality of generated taxonomies by reducing hallucinations. We evaluate the proposed framework using benchmark taxonomies under a masked taxonomy expansion setting and compare multiple validation strategies. Experimental results, supported by both adapted evaluation metrics and human evaluation, demonstrate that ReLTEx produces more reliable and semantically coherent taxonomy expansions.

Zeinab Ghamlouch, Mehwish Alam

Télécom Paris, Institut Polytechnique de Paris, France

LLM Hallucination Mitigation LLM Reliability

Ask PDF

Oct 11, 2026

Latent Taxonomies: How Property Induction Develops in Language Model Pre-training

When told that robins have sesamoid bones, people are far more prone to extend the property to sparrows than to whales. This behavior, called category-based property induction, is well documented in humans, but whether and how it develops in language models trained only to predict the next token is unclear. To shed light on this, we construct a hierarchical taxonomy of synthetic entities grouped by the properties they share. We then inject facts from this latent taxonomy into the continued pre-training of Pythia and OLMo 2 models from 70M to 7B parameters, and track the development of inductive behaviors. We find that taxonomically aligned induction emerges from next-token prediction alone: a property learned for one entity transfers more strongly within its taxonomic category than across categories. Internally, entities that share a deeper category become more similar in activation space, and clustering recovers the full taxonomic tree from entity representations. Contrary to the usual expectation that scale helps, we find that induction weakens with model size when the data budget is fixed, suggesting that larger models memorize individual facts rather than compress them into shared structure. Induction also strengthens with more pre-training before the taxonomy injection, transfers to novel in-context properties, and can be overridden by a latent taxonomy implied by the prompt. Together, these results show that a model's inductive generalization reflects the latent organization of its training data, with implications for data curation and for predicting how far a learned fact will spread.

Jan Sobotka, Ekaterina Goliakova, Marcin Detyniecki +2

EPFL · AXA · Sorbonne University, CNRS, LIP6 +1

Inductive Reasoning in Language Models Inductive Inference Implicit Reasoning in Language Models Language Model Pretraining Factual Knowledge in Language Models Representation Geometry in Language Models

Ask PDF

Abstract

Taxonomy Induction

Explore similar work

SPARROW: Scalable Taxonomy Induction via Structure-Preserving Partitioning and Constraint-Guided Merging

ReLTEx: Reliable LLM-based Taxonomy Expansion

Latent Taxonomies: How Property Induction Develops in Language Model Pre-training