Optimized Algorithms for Text Clustering with LLM-Generated Constraints

2026-01-16

AI Summary

This work addresses the high annotation cost and noise sensitivity of traditional constrained text clustering methods that rely on pairwise must-link/cannot-link constraints. While large language models (LLMs) offer promise for automatically generating such constraints, their practical use is hindered by excessive query costs and noisy outputs. To overcome these limitations, the authors propose an efficient LLM-driven clustering approach that replaces pairwise constraints with set-level constraints, drastically reducing the number of LLM invocations. They further design a clustering algorithm tailored to the characteristics of LLM-generated constraints and incorporate confidence thresholds and penalty mechanisms to mitigate the impact of noise. Experiments on five benchmark datasets demonstrate that the proposed method achieves clustering accuracy comparable to state-of-the-art approaches while reducing LLM query counts by over 20-fold.

Technology Category

• Machine Learning: Clustering
• Natural Language Processing: (Large) Language Models
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• text clustering
• large language models
• constraint generation
• must-link constraints
• cannot-link constraints

Innovation

• constraint generation
• text clustering
• large language models
• constrained clustering
• query efficiency