TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912426910285824 |
|---|---|
| author | Kargupta, Priyanka Zhang, Nan Zhang, Yunyi Zhang, Rui Mitra, Prasenjit Han, Jiawei |
| author_facet | Kargupta, Priyanka Zhang, Nan Zhang, Yunyi Zhang, Rui Mitra, Prasenjit Han, Jiawei |
| contents | The rapid evolution of scientific fields introduces challenges in organizing and retrieving scientific literature. While expert-curated taxonomies have traditionally addressed this need, the process is time-consuming and expensive. Furthermore, recent automatic taxonomy construction methods either (1) over-rely on a specific corpus, sacrificing generalizability, or (2) depend heavily on the general knowledge of large language models (LLMs) contained within their pre-training datasets, often overlooking the dynamic nature of evolving scientific domains. Additionally, these approaches fail to account for the multi-faceted nature of scientific literature, where a single research paper may contribute to multiple dimensions (e.g., methodology, new tasks, evaluation metrics, benchmarks). To address these gaps, we propose TaxoAdapt, a framework that dynamically adapts an LLM-generated taxonomy to a given corpus across multiple dimensions. TaxoAdapt performs iterative hierarchical classification, expanding both the taxonomy width and depth based on corpus' topical distribution. We demonstrate its state-of-the-art performance across a diverse set of computer science conferences over the years to showcase its ability to structure and capture the evolution of scientific fields. As a multidimensional method, TaxoAdapt generates taxonomies that are 26.51% more granularity-preserving and 50.41% more coherent than the most competitive baselines judged by LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_10737 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora Kargupta, Priyanka Zhang, Nan Zhang, Yunyi Zhang, Rui Mitra, Prasenjit Han, Jiawei Computation and Language Information Retrieval The rapid evolution of scientific fields introduces challenges in organizing and retrieving scientific literature. While expert-curated taxonomies have traditionally addressed this need, the process is time-consuming and expensive. Furthermore, recent automatic taxonomy construction methods either (1) over-rely on a specific corpus, sacrificing generalizability, or (2) depend heavily on the general knowledge of large language models (LLMs) contained within their pre-training datasets, often overlooking the dynamic nature of evolving scientific domains. Additionally, these approaches fail to account for the multi-faceted nature of scientific literature, where a single research paper may contribute to multiple dimensions (e.g., methodology, new tasks, evaluation metrics, benchmarks). To address these gaps, we propose TaxoAdapt, a framework that dynamically adapts an LLM-generated taxonomy to a given corpus across multiple dimensions. TaxoAdapt performs iterative hierarchical classification, expanding both the taxonomy width and depth based on corpus' topical distribution. We demonstrate its state-of-the-art performance across a diverse set of computer science conferences over the years to showcase its ability to structure and capture the evolution of scientific fields. As a multidimensional method, TaxoAdapt generates taxonomies that are 26.51% more granularity-preserving and 50.41% more coherent than the most competitive baselines judged by LLMs. |
| title | TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2506.10737 |