Large Language Models Enable Few-Shot Clustering
Viswanathan, Vijay, Gashteovski, Kiril, Lawrence, Carolin, Wu, Tongshuang, Neubig, Graham
–arXiv.org Artificial Intelligence
Unlike traditional unsupervised clustering, semi-supervised clustering allows users to provide meaningful structure to the data, which helps the clustering algorithm to match the user's intent. Existing approaches to semi-supervised clustering require a significant amount of feedback from an expert to improve the clusters. In this paper, we ask whether a large language model can amplify an expert's guidance to enable query-efficient, few-shot semi-supervised text clustering. We show that LLMs are surprisingly effective at improving clustering. We explore three stages where LLMs can be incorporated into clustering: before clustering (improving input features), during clustering (by providing constraints to the clusterer), and after clustering (using LLMs post-correction). We find incorporating LLMs in the first two stages can routinely provide significant improvements in cluster quality, and that LLMs enable a user to make trade-offs between cost and accuracy to produce desired clusters. We release our code and LLM prompts for the public to use.
arXiv.org Artificial Intelligence
Jul-2-2023
- Country:
- North America
- United States
- District of Columbia > Washington (0.04)
- New York > New York County
- New York City (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Canada > Ontario
- Toronto (0.04)
- United States
- Europe
- United Kingdom (0.14)
- Belgium > Flanders (0.04)
- France > Provence-Alpes-Côte d'Azur
- Bouches-du-Rhône > Marseille (0.05)
- Asia
- Middle East > Palestine (0.04)
- China > Hong Kong (0.04)
- Africa > Middle East
- Egypt (0.04)
- North America
- Genre:
- Research Report (0.50)
- Industry:
- Leisure & Entertainment (1.00)
- Media > Film (0.94)
- Government > Regional Government
- Technology: