Semantic-Augmented Latent Topic Modeling with LLM-in-the-Loop
This work addresses the challenge of enhancing topic modeling for text mining applications, but it is incremental as it builds on existing LDA methods with LLM integration.
The paper tackled the problem of improving topic modeling by integrating Large Language Models (LLMs) into Latent Dirichlet Allocation (LDA) for initialization and post-correction, finding that LLM-guided initialization did not enhance convergence and performed worst, while LLM-enabled post-correction achieved a 5.86% improvement in coherence.
Latent Dirichlet Allocation (LDA) is a prominent generative probabilistic model used for uncovering abstract topics within document collections. In this paper, we explore the effectiveness of augmenting topic models with Large Language Models (LLMs) through integration into two key phases: Initialization and Post-Correction. Since the LDA is highly dependent on the quality of its initialization, we conduct extensive experiments on the LLM-guided topic clustering for initializing the Gibbs sampling algorithm. Interestingly, the experimental results reveal that while the proposed initialization strategy improves the early iterations of LDA, it has no effect on the convergence and yields the worst performance compared to the baselines. The LLM-enabled post-correction, on the other hand, achieved a promising improvement of 5.86% in the coherence evaluation. These results highlight the practical benefits of the LLM-in-the-loop approach and challenge the belief that LLMs are always the superior text mining alternative.