TR-GPT-CF: A Topic Refinement Method Using GPT and Coherence Filtering

Abstract

Traditional topic models are effective at uncovering patterns within large text corpora but often struggle with capturing the contextual nuances necessary for meaningful interpretation. As a result, these models may produce incoherent topics, making it challenging to achieve consistency and clarity in topic interpretation—limitations that hinder their utility for real-world applications requiring reliable insights. To overcome these challenges, we introduce a novel post-extracted topic refinement approach that uses Z-score centroid-based misaligned word detection and hybrid semantic–contextual word replacement with WordNet and GPT to replace misaligned words within topics. Evaluations across multiple datasets reveal that our approach significantly enhances topic coherence, providing a robust solution for more interpretable and semantically coherent topics.