# Generative AI for automatic topic labelling

arXiv: https://arxiv.org/abs/2408.07003 · HTML: https://mlsanity.com/paper/2408.07003/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 2 references that are in the map.
- First posted on arXiv 13 Aug 2024.

## Built on by (most cited first, 5 of 5)

- [Generative AI and the future of scientometrics: current topics and future questions](https://mlsanity.com/paper/2507.00783/) (2025)
- [Toward a Safer Web: Multilingual Multi-Agent LLMs for Mitigating Adversarial Misinformation Attacks](https://mlsanity.com/paper/2510.08605/) (2025)
- [Bias Testing and Mitigation in Black Box LLMs using Metamorphic Relations](https://mlsanity.com/paper/2512.00556/) (2025)
- [AgriLens: Semantic Retrieval in Agricultural Texts Using Topic Modeling and Language Models](https://mlsanity.com/paper/2601.08283/) (2026)
- [From Documents to Segments: A Contextual Reformulation for Topic Assignment](https://mlsanity.com/paper/2605.17714/) (2026)

## Abstract (arXiv)

Topic Modeling has become a prominent tool for the study of scientific fields, as they allow for a large scale interpretation of research trends. Nevertheless, the output of these models is structured as a list of keywords which requires a manual interpretation for the labelling. This paper proposes to assess the reliability of three LLMs, namely flan, GPT-4o, and GPT-4 mini for topic labelling. Drawing on previous research leveraging BERTopic, we generate topics from a dataset of all the scientific articles (n=34,797) authored by all biology professors in Switzerland (n=465) between 2008 and 2020, as recorded in the Web of Science database. We assess the output of the three models both quantitatively and qualitatively and find that, first, both GPT models are capable of accurately and precisely label topics from the models' output keywords. Second, 3-word labels are preferable to grasp the complexity of research topics.