TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora

• URL: http://arxiv.org/abs/2506.10737v1
• Date: Thu, 12 Jun 2025 14:26:28 GMT
• Title: TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora
• Authors: Priyanka Kargupta, Nan Zhang, Yunyi Zhang, Rui Zhang, Prasenjit Mitra, Jiawei Han,
• Abstract summary: TaxoAdapt is a framework that adapts an LLM-generated taxonomy to a given corpus across multiple dimensions.<n>We demonstrate its state-of-the-art performance across a diverse set of computer science conferences.
• Score: 34.103517830260365
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Science Hierarchography: Hierarchical Organization of Science Literature [20.182213614072836]
  We motivate SCIENCE HARCHOGRAPHY, the goal of organizing scientific literature into a high-quality hierarchical structure.<n>We develop a range of algorithms to achieve the goals of SCIENCE HIERARCHOGRAPHY.<n>Results show that this structured approach enhances interpretability, supports trend discovery, and offers an alternative pathway for exploring scientific literature beyond traditional search methods.
  arXiv  Detail & Related papers  (2025-04-18T17:59:29Z)
• Can Large Language Models Serve as Effective Classifiers for Hierarchical Multi-Label Classification of Scientific Documents at Industrial Scale? [1.0562108865927007]
  Large Language Models (LLMs) have demonstrated great potential in complex tasks such as multi-label classification.<n>We present methods that combine the strengths of LLMs with dense retrieval techniques to overcome these challenges.<n>We evaluate the effectiveness of our methods on SSRN, a large repository of preprints spanning multiple disciplines.
  arXiv  Detail & Related papers  (2024-12-06T15:51:22Z)
• Are Large Language Models a Good Replacement of Taxonomies? [25.963448807848746]
  Large language models (LLMs) demonstrate an impressive ability to internalize knowledge and answer natural language questions. We ask if the schema of knowledge graph (i.e., taxonomy) is made obsolete by LLMs.
  arXiv  Detail & Related papers  (2024-06-17T01:21:50Z)
• A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery [68.48094108571432]
  Large language models (LLMs) have revolutionized the way text and other modalities of data are handled. We aim to provide a more holistic view of the research landscape by unveiling cross-field and cross-modal connections between scientific LLMs.
  arXiv  Detail & Related papers  (2024-06-16T08:03:24Z)
• FLAME: Self-Supervised Low-Resource Taxonomy Expansion using Large Language Models [19.863010475923414]
  Taxonomies find utility in various real-world applications, such as e-commerce search engines and recommendation systems. Traditional supervised taxonomy expansion approaches encounter difficulties stemming from limited resources. We propose FLAME, a novel approach for taxonomy expansion in low-resource environments by harnessing the capabilities of large language models.
  arXiv  Detail & Related papers  (2024-02-21T08:50:40Z)
• Scientific Large Language Models: A Survey on Biological & Chemical Domains [47.97810890521825]
  Large Language Models (LLMs) have emerged as a transformative power in enhancing natural language comprehension. The application of LLMs extends beyond conventional linguistic boundaries, encompassing specialized linguistic systems developed within various scientific disciplines. As a burgeoning area in the community of AI for Science, scientific LLMs warrant comprehensive exploration.
  arXiv  Detail & Related papers  (2024-01-26T05:33:34Z)
• Taxonomy Enrichment with Text and Graph Vector Representations [61.814256012166794]
  We address the problem of taxonomy enrichment which aims at adding new words to the existing taxonomy. We present a new method that allows achieving high results on this task with little effort. We achieve state-of-the-art results across different datasets and provide an in-depth error analysis of mistakes.
  arXiv  Detail & Related papers  (2022-01-21T09:01:12Z)
• Using Full-text Content of Academic Articles to Build a Methodology Taxonomy of Information Science in China [10.949304105928286]
  This study provides new concepts for constructing a methodology taxonomy of information science. The proposed methodology taxonomy is more detailed than conventional schemes and the speed of taxonomy renewal has been enhanced.
  arXiv  Detail & Related papers  (2021-01-20T01:56:43Z)
• Octet: Online Catalog Taxonomy Enrichment with Self-Supervision [67.26804972901952]
  We present a self-supervised end-to-end framework, Octet for Online Catalog EnrichmenT. We propose to train a sequence labeling model for term extraction and employ graph neural networks (GNNs) to capture the taxonomy structure. Octet enriches an online catalog in production to 2 times larger in the open-world evaluation.
  arXiv  Detail & Related papers  (2020-06-18T04:53:07Z)
• TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network [62.12557274257303]
  Taxonomies consist of machine-interpretable semantics and provide valuable knowledge for many web applications. We propose a novel self-supervised framework, named TaxoExpan, which automatically generates a set of query concept, anchor concept> pairs from the existing taxonomy as training data. We develop two innovative techniques in TaxoExpan: (1) a position-enhanced graph neural network that encodes the local structure of an anchor concept in the existing taxonomy, and (2) a noise-robust training objective that enables the learned model to be insensitive to the label noise in the self-supervision data.
  arXiv  Detail & Related papers  (2020-01-26T21:30:21Z)

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.