Optimized Algorithms for Text Clustering with LLM-Generated Constraints

TL;DR

This paper presents a novel constraint-generation method using large language models to improve text clustering accuracy efficiently, reducing resource consumption and maintaining high performance.

Contribution

It introduces a new approach that generates constraint sets instead of pairwise constraints, enhancing query efficiency and accuracy in LLM-based text clustering.

Findings

Achieves comparable clustering accuracy to state-of-the-art methods.

Reduces LLM query costs by over 20 times.

Effectively handles potentially inaccurate constraints with confidence thresholds.

Abstract

Clustering is a fundamental tool that has garnered significant interest across a wide range of applications including text analysis. To improve clustering accuracy, many researchers have incorporated background knowledge, typically in the form of must-link and cannot-link constraints, to guide the clustering process. With the recent advent of large language models (LLMs), there is growing interest in improving clustering quality through LLM-based automatic constraint generation. In this paper, we propose a novel constraint-generation approach that reduces resource consumption by generating constraint sets rather than using traditional pairwise constraints. This approach improves both query efficiency and constraint accuracy compared to state-of-the-art methods. We further introduce a constrained clustering algorithm tailored to the characteristics of LLM-generated constraints. Our method incorporates a confidence threshold and a penalty mechanism to address potentially inaccurate constraints. We evaluate our approach on five text datasets, considering both the cost of constraint generation and the overall clustering performance. The results show that our method achieves clustering accuracy comparable to the state-of-the-art algorithms while reducing the number of LLM queries by more than 20 times.