Large Language Models Enable Few-Shot Clustering
Vijay Viswanathan, Kiril Gashteovski, Kiril Gashteovski, Carolin Lawrence, Tongshuang Wu, Graham Neubig
Abstract
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 (LLM) 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 that incorporating LLMs in the first two stages routinely provides 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.1- Anthology ID:
- 2024.tacl-1.18
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 12
- Month:
- Year:
- 2024
- Address:
- Cambridge, MA
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 321–333
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/2024.tacl-1.18/
- DOI:
- 10.1162/tacl_a_00648
- Cite (ACL):
- Vijay Viswanathan, Kiril Gashteovski, Kiril Gashteovski, Carolin Lawrence, Tongshuang Wu, and Graham Neubig. 2024. Large Language Models Enable Few-Shot Clustering. Transactions of the Association for Computational Linguistics, 12:321–333.
- Cite (Informal):
- Large Language Models Enable Few-Shot Clustering (Viswanathan et al., TACL 2024)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/2024.tacl-1.18.pdf