Large Language Models Offer an Alternative to the Traditional Approach of Topic Modelling
Preprint
Abstract
Topic modelling, as a well-established unsupervised technique, has found extensive use in automatically detecting significant topics within a corpus of documents. However, classic topic modelling approaches (e.g., LDA) have certain drawbacks, such as the lack of semantic understanding and the presence of overlapping topics. In this work, we investigate the untapped potential of large language models (LLMs) as an alternative for uncovering the underlying topics within extensive text corpora. To this end, we introduce a framework that prompts LLMs to generate topics from a given set of documents and establish evaluation protocols to assess the clustering efficacy of LLMs. Our findings indicate that LLMs with appropriate prompts can stand out as a viable alternative, capable of generating relevant topic titles and adhering to human guidelines to refine and merge topics. Through in-depth experiments and evaluation, we summarise the advantages and constraints of employing LLMs in topic extraction.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Benchmarking Large Language Models for News SummarizationTransactions of the Association for Computational Linguistics, 2024
- Large Language Models are Diverse Role-Players for Summarization Evaluation2023
- Evaluating large language models on medical evidence summarizationnpj Digital Medicine, 2023
- The interpretation of topic models for scholarly analysis: An evaluation and critique of current practiceDigital Scholarship in the Humanities, 2022
- Topic modeling algorithms and applications: A surveyInformation Systems, 2022
- DeepSumm: Exploiting topic models and sequence to sequence networks for extractive text summarizationExpert Systems with Applications, 2022
- A topic modeled unsupervised approach to single document extractive text summarizationKnowledge-Based Systems, 2022
- Classification aware neural topic model for COVID-19 disinformation categorisationPLOS ONE, 2021
- Anchored Correlation Explanation: Topic Modeling with Minimal Domain KnowledgeTransactions of the Association for Computational Linguistics, 2017
- Comparing Apples to Apple: The Effects of Stemmers on Topic ModelsTransactions of the Association for Computational Linguistics, 2016