Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

TopicGPT: A Prompt-based Topic Modeling Framework

About

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.

Chau Minh Pham, Alexander Hoyle, Simeng Sun, Philip Resnik, Mohit Iyyer• 2023

Related benchmarks

TaskDatasetResultRank
Passage-pair linkingLiterary analysis corpus (Goodreads, Sparknotes, Litcharts)
Precision14.8
41
Topic Relatedness AssessmentLiterary passage sets 50 (Evaluation)
Very Related48
33
Topic ModelingWiki
Purity0.422
8
Topic ModelingBills
P1 Score0.399
8
Topic ModelingBanking77
Purity0.184
7
Topic Modeling50 literary passages Human Evaluation (test)
Topic 1 Score2.64
6
Hierarchical classificationWikipedia (held-out set)
NMI0.7
3
Hierarchical classificationUS Bills (held-out set)
NMI0.51
3
Showing 8 of 8 rows

Other info

Follow for update