TopicGPT: A Prompt-based Topic Modeling Framework
Not on the map. Why?
Abstract (arXiv)
Topic modeling is a well-established technique for exploring text corpora. Conventional topic models (e.g., LDA) represent topics as bags of words that often require "reading the tea leaves" to interpret; additionally, they offer users minimal control over the formatting and specificity of resulting topics. To tackle these issues, we introduce TopicGPT, a prompt-based framework that uses large language models (LLMs) to uncover latent topics in a text collection. TopicGPT produces topics that align better with human categorizations compared to competing methods: it achieves a harmonic mean purity of 0.74 against human-annotated Wikipedia topics compared to 0.64 for the strongest baseline. Its topics are also interpretable, dispensing with ambiguous bags of words in favor of topics with natural language labels and associated free-form descriptions. Moreover, the framework is highly adaptable, allowing users to specify constraints and modify topics without the need for model retraining. By streamlining access to high-quality and interpretable topics, TopicGPT represents a compelling, human-centered approach to topic modeling.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 51 references that are in the map. First posted on arXiv 2 Nov 2023.
Builds on
18 of 51 references.
References · 18
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
- 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 779
- 2017Regularizing and Optimizing LSTM Language Modelscited by 205
- 2017Autoencoding Variational Inference For Topic Modelscited by 168
- 2023Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Promptingcited by 163
- 2020Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherencecited by 121
- 2023Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptationcited by 79
- 2021Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherencecited by 74
- 2020Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!cited by 73
- 2023Large Language Models Enable Few-Shot Clusteringcited by 72
- 2023ClusterLLM: Large Language Models as a Guide for Text Clusteringcited by 69
6 more
- 2023LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Codingcited by 64
- 2023PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documentscited by 61
- 2023Goal-Driven Explainable Clustering via Language Descriptionscited by 58
- 2020Topic Modeling with Contextualized Word Representation Clusterscited by 41
- 2023Natural Language Decompositions of Implicit Content Enable Better Text Representationscited by 18
- 2020A Topic Coverage Approach to Evaluation of Topic Modelscited by 7
Built on by
Citing papers per year: 2026: 1.
1 paper.