# Semantic-Augmented Latent Topic Modeling with LLM-in-the-Loop

arXiv: https://arxiv.org/abs/2507.08498 · HTML: https://mlsanity.com/paper/2507.08498/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 37 references that are in the map.
- First posted on arXiv 11 Jul 2025.

## Builds on (most cited first, 8 of 8)

- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning](https://mlsanity.com/paper/2301.11916/) (2023)
- [Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence](https://mlsanity.com/paper/2004.03974/) (2020)
- [Large Language Models Enable Few-Shot Clustering](https://mlsanity.com/paper/2307.00524/) (2023)
- [Large Language Models Offer an Alternative to the Traditional Approach of Topic Modelling](https://mlsanity.com/paper/2403.16248/) (2024)
- [Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues](https://mlsanity.com/paper/2412.09049/) (2024)
- [Familia: A Configurable Topic Modeling Framework for Industrial Text Engineering](https://mlsanity.com/paper/1808.03733/) (2018)
- [Contextual ASR Error Handling with LLMs Augmentation for Goal-Oriented Conversational AI](https://mlsanity.com/paper/2501.06129/) (2025)

## Abstract (arXiv)

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.