LITA: An Efficient LLM-assisted Iterative Topic Augmentation Framework

TL;DR

LITA is a novel framework that combines user seeds, embedding clustering, and LLMs for efficient, high-quality topic modeling with reduced API costs, outperforming existing methods.

Contribution

It introduces an iterative, LLM-assisted topic augmentation approach that improves relevance and coherence while minimizing API usage.

Findings

LITA outperforms baseline models in topic quality and clustering metrics.

The framework reduces API costs compared to traditional LLM applications.

Experiments demonstrate enhanced topic coherence and relevance.

Abstract

Topic modeling is widely used for uncovering thematic structures within text corpora, yet traditional models often struggle with specificity and coherence in domain-focused applications. Guided approaches, such as SeededLDA and CorEx, incorporate user-provided seed words to improve relevance but remain labor-intensive and static. Large language models (LLMs) offer potential for dynamic topic refinement and discovery, yet their application often incurs high API costs. To address these challenges, we propose the LLM-assisted Iterative Topic Augmentation framework (LITA), an LLM-assisted approach that integrates user-provided seeds with embedding-based clustering and iterative refinement. LITA identifies a small number of ambiguous documents and employs an LLM to reassign them to existing or new topics, minimizing API costs while enhancing topic quality. Experiments on two datasets across topic quality and clustering performance metrics demonstrate that LITA outperforms five baseline models, including LDA, SeededLDA, CorEx, BERTopic, and PromptTopic. Our work offers an efficient and adaptable framework for advancing topic modeling and text clustering.