Hierarchical Text Classification with LLM-Refined Taxonomies

TL;DR

This paper introduces TaxMorph, a framework that uses large language models to refine hierarchical taxonomies, leading to improved text classification performance by better aligning the taxonomy structure with model semantics.

Contribution

TaxMorph is the first method to revise entire taxonomies using LLMs, enhancing HTC by improving taxonomy-model alignment and outperforming human-curated hierarchies.

Findings

LLM-refined taxonomies outperform human-curated ones in F1 score by up to +2.9pp.

Refined taxonomies align more closely with model confusion patterns.

Human-curated taxonomies produce more separable clusters in embedding space.

Abstract

Hierarchical text classification (HTC) depends on taxonomies that organize labels into structured hierarchies. However, many real-world taxonomies introduce ambiguities, such as identical leaf names under similar parent nodes, which prevent language models (LMs) from learning clear decision boundaries. In this paper, we present TaxMorph, a framework that uses large language models (LLMs) to transform entire taxonomies through operations such as renaming, merging, splitting, and reordering. Unlike prior work, our method revises the full hierarchy to better match the semantics encoded by LMs. Experiments across three HTC benchmarks show that LLM-refined taxonomies consistently outperform human-curated ones in various settings up to +2.9pp. in F1. To better understand these improvements, we compare how well LMs can assign leaf nodes to parent nodes and vice versa across human-curated and LLM-refined taxonomies. We find that human-curated taxonomies lead to more easily separable clusters in embedding space. However, the LLM-refined taxonomies align more closely with the model's actual confusion patterns during classification. In other words, even though they are harder to separate, they better reflect the model's inductive biases. These findings suggest that LLM-guided refinement creates taxonomies that are more compatible with how models learn, improving HTC performance.