Revisiting Automated Topic Model Evaluation with Large Language Models

Dominik Stammbach, Vilém Zouhar, Alexander Hoyle, Mrinmaya Sachan, Elliott Ash

Submission Type: Regular Short Paper

Submission Track: Theme Track: Large Language Models and the Future of NLP

Submission Track 2: Information Retrieval and Text Mining

Keywords: topic model evaluation, interpretability, large language models, text clustering

TL;DR: Automatically evaluating topic model output has been a longstanding challenge; we find that large language models turn out to be very good at this task.

Abstract: Topic models help us make sense of large text collections. Automatically evaluating their output and determining the optimal number of topics are both longstanding challenges, with no effective automated solutions to date. This paper proposes using large language models (LLMs) for these tasks. We find that LLMs appropriately assess the resulting topics, correlating more strongly with human judgments than existing automated metrics. However, the setup of the evaluation task is crucial — LLMs perform better on coherence ratings of word sets than on intrustion detection. We find that LLMs can also assist us in guiding us towards a reasonable number of topics. In actual applications, topic models are typically used to answer a research question related to a collection of texts. We can incorporate this research question in the prompt to the LLM, which helps estimating the optimal number of topics.

Submission Number: 1499