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

• URL: http://arxiv.org/abs/2605.12520v1
• Date: Fri, 03 Apr 2026 15:48:09 GMT
• Title: BoostTaxo: Zero-Shot Taxonomy Induction via Boosting-Style Agentic Reasoning and Constraint-Aware Calibration
• Abstract summary: BoostTaxo is a boosting-style LLM framework for zero-shot taxonomy induction.<n>It takes a set of domain terms as inputs and performs parent identification in a coarse-to-fine manner.<n>It employs retrieval-augmented definition refinement, hybrid parent candidate selection, candidate rating, and structure-aware score calibration.<n>It achieves superior or comparable performance to state-of-the-art methods in zero-shot taxonomy induction.
• Score: 6.719751155411076
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• TaxCE : A Framework for Automated Taxonomy Construction and Evaluation at Scale [0.992650024444822]
  TaxCE is a fully automated framework for organizing unstructured feedback text into hierarchical taxonomy.<n>We introduce three corpus-grounded evaluation metrics, Exclusivity, Exhaustivity, and Granularity (EEG), and integrate them into a metrics-in-the-loop iterative refinement mechanism.
  arXiv  Detail & Related papers  (2026-08-31T11:25:25Z)
• Preference Data Selection for Mitigating the Alignment Tax in Large Language Models [52.18310687523229]
  BALIGN is a balanced data selection strategy that mitigates catastrophic forgetting while optimizing alignment efficacy.<n>By aggregating three key data-centric features into a unified composite risk score, BALIGN systematically filters out high-risk preference samples.<n>Experiments on standard human preference datasets demonstrate that BALIGN strongly preserves foundational capabilities without compromising alignment gains.
  arXiv  Detail & Related papers  (2026-08-25T07:58:42Z)
• Selective Ensemble Based on Preference-Directed Multi-Objective Bandits [90.75513823660775]
  We formalize a sequential decision problem under partially specified linear preferences.<n>We then propose a preference-directed upper confidence bound (PrefUCB) algorithm.<n> Experiments on large pre-trained model selective ensemble tasks and online asset allocation under institutional mandates validate our method.
  arXiv  Detail & Related papers  (2026-06-20T07:52:46Z)
• Automating Categorization of Scientific Texts with In-Context Learning and Prompt-Chaining in Large Language Models [4.1824815480811806]
  This study systematically evaluates the performance of off-the-shelf Large Language Models (LLMs) in analyzing scientific texts.<n>We investigated the effectiveness of advanced prompt engineering strategies, namely In-Context Learning (ICL) and Prompt Chaining.<n>Our experiments demonstrate that Prompt Chaining yields superior classification accuracy compared to pure ICL.
  arXiv  Detail & Related papers  (2026-04-25T19:52:21Z)
• Evaluating LLM-Based Grant Proposal Review via Structured Perturbations [18.689211845609623]
  We develop a perturbation-based framework probing LLM sensitivity across six quality axes.<n>We compare three review architectures: single-pass review, section-by-section analysis, and a 'Council of Personas' ensemble emulating expert panels.
  arXiv  Detail & Related papers  (2026-03-09T11:53:50Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• Supervised Optimism Correction: Be Confident When LLMs Are Sure [91.7459076316849]
  We establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning.<n>We show that the widely used beam search method suffers from unacceptable over-optimism.<n>We propose Supervised Optimism Correction, which introduces a simple yet effective auxiliary loss for token-level $Q$-value estimations.
  arXiv  Detail & Related papers  (2025-04-10T07:50:03Z)
• LITE: LLM-Impelled efficient Taxonomy Evaluation [32.8374687916129]
  LITE is a top-down hierarchical taxonomy evaluation strategy, breaking down the taxonomy into manageable substructures.<n>It provides both quantitative performance analysis and qualitative insights by integrating evaluation metrics closely aligned with task objectives.
  arXiv  Detail & Related papers  (2025-04-02T05:33:05Z)
• A Multi-Stage Framework with Taxonomy-Guided Reasoning for Occupation Classification Using Large Language Models [17.953087038185778]
  Large language models (LLMs) hold promise due to their extensive world knowledge and in-context learning capabilities.<n>Our framework integrates taxonomy-guided reasoning examples to enhance performance by aligning outputs with taxonomic knowledge.<n> Evaluations on a large-scale dataset show that our framework not only enhances occupation and skill classification tasks, but also provides a cost-effective alternative to frontier models.
  arXiv  Detail & Related papers  (2025-03-17T09:44:50Z)
• ProTeCt: Prompt Tuning for Taxonomic Open Set Classification [59.59442518849203]
  Few-shot adaptation methods do not fare well in the taxonomic open set (TOS) setting. We propose a prompt tuning technique that calibrates the hierarchical consistency of model predictions. A new Prompt Tuning for Hierarchical Consistency (ProTeCt) technique is then proposed to calibrate classification across label set granularities.
  arXiv  Detail & Related papers  (2023-06-04T02:55:25Z)
• When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning [62.00672284480755]
  This paper aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving.
  arXiv  Detail & Related papers  (2023-02-15T04:14:20Z)
• Enquire One's Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy Expansion [17.399482876574407]
  We propose the Hierarchy Expansion Framework (HEF), which fully exploits the hierarchical structure's properties to maximize the coherence of expanded taxonomy. HEF vastly surpasses the prior state-of-the-art on three benchmark datasets by an average improvement of 46.7% in accuracy and 32.3% in mean reciprocal rank.
  arXiv  Detail & Related papers  (2021-01-27T08:57:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.