Published In

2025 IEEE International Conference on Big Data (bigdata)

Document Type

Pre-Print

Publication Date

2025

Subjects

Machine learning methods

Abstract

Topic discovery in scientific literature provides valuable insights for researchers to identify emerging trends and explore new avenues for investigation, facilitating easier scientific information retrieval. Many machine learning methods, particularly deep embedding techniques, have been applied to discover research topics. However, most existing topic discovery methods rely on word embedding to capture the semantics and lack a comprehensive understanding of scientific publications, struggling with complex, high-dimensional text relationships. Inspired by the exceptional comprehension of textual information by large language models (LLMs), we propose an advanced topic discovery method enhanced by LLMs to improve scientific topic identification, namely SciTopic. Specifically, we first build a textual encoder to capture the content from scientific publications, including metadata, title, and abstract. Next, we construct a space optimization module that integrates entropy-based sampling and triplet tasks guided by LLMs, enhancing the focus on thematic relevance and contextual intricacies between ambiguous instances. Then, we propose to fine-tune the textual encoder based on the guidance from the LLMs by optimizing the contrastive loss of the triplets, forcing the text encoder to better discriminate instances of different topics. Finally, extensive experiments conducted on three real-world datasets of scientific publications demonstrate that SciTopic outperforms the state-of-the-art (SOTA) scientific topic discovery methods, enabling researchers to gain deeper and faster insights11Access the source code link: https://github.com/CNICDS/SciTopic.

Rights

Copyright (c) 2026 The Authors

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Description

This is the author’s version of a work that was accepted for publication. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published as: (2025). SciTopic: Enhancing Topic Discovery in Scientific Literature Through Advanced LLM. 2025 IEEE International Conference on Big Data (BigData), 1974–1983. https://doi.org/10.1109/bigdata66926.2025.11401030

DOI

10.1109/BigData66926.2025.11401030

Persistent Identifier

https://archives.pdx.edu/ds/psu/44580

Publisher

IEEE

Download

Share

COinS