# TopicTag: Automatic Annotation of NMF Topic Models Using Chain of Thought and Prompt Tuning with LLMs

arXiv: https://arxiv.org/abs/2407.19616 · HTML: https://mlsanity.com/paper/2407.19616/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 21 references that are in the map.
- First posted on arXiv 29 Jul 2024.

## Builds on (most cited first, 4 of 4)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Multi-document Summarization via Deep Learning Techniques: A Survey](https://mlsanity.com/paper/2011.04843/) (2020)
- [Open Domain Multi-document Summarization: A Comprehensive Study of Model Brittleness under Retrieval](https://mlsanity.com/paper/2212.10526/) (2022)
- [SeNMFk-SPLIT: Large Corpora Topic Modeling by Semantic Non-negative Matrix Factorization with Automatic Model Selection](https://mlsanity.com/paper/2208.09942/) (2022)

## Built on by (most cited first, 3 of 3)

- [Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization](https://mlsanity.com/paper/2502.20364/) (2025)
- [BEYONDWORDS is All You Need: Agentic Generative AI based Social Media Themes Extractor](https://mlsanity.com/paper/2503.01880/) (2025)
- [From Documents to Segments: A Contextual Reformulation for Topic Assignment](https://mlsanity.com/paper/2605.17714/) (2026)

## Abstract (arXiv)

Topic modeling is a technique for organizing and extracting themes from large collections of unstructured text. Non-negative matrix factorization (NMF) is a common unsupervised approach that decomposes a term frequency-inverse document frequency (TF-IDF) matrix to uncover latent topics and segment the dataset accordingly. While useful for highlighting patterns and clustering documents, NMF does not provide explicit topic labels, necessitating subject matter experts (SMEs) to assign labels manually. We present a methodology for automating topic labeling in documents clustered via NMF with automatic model determination (NMFk). By leveraging the output of NMFk and employing prompt engineering, we utilize large language models (LLMs) to generate accurate topic labels. Our case study on over 34,000 scientific abstracts on Knowledge Graphs demonstrates the effectiveness of our method in enhancing knowledge management and document organization.