Skip to content
conftrace_
2026 EMNLP EMNLP 2026

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

AbstractTaxonomy 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, as measured by Ancestor F1, across backbones. The code is available at https://github.com/rebeccazyr/SPARROW.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Knowledge & Reasoning

More from EMNLP 2026

All EMNLP 2026 papers →