Context-Aware Clustering using Large Language Models

TL;DR

This paper presents CACTUS, a novel context-aware clustering method using open-source LLMs with a new triplet loss and self-supervised tasks, enabling efficient supervised clustering of text entities with improved accuracy.

Contribution

The paper introduces CACTUS, a scalable approach leveraging open-source LLMs, a novel augmented triplet loss, and self-supervised techniques for supervised text clustering.

Findings

CACTUS outperforms existing clustering baselines on e-commerce datasets.

The method effectively transfers knowledge from closed-source to open-source LLMs.

Scalable and cost-effective clustering with improved accuracy.

Abstract

Despite the remarkable success of Large Language Models (LLMs) in text understanding and generation, their potential for text clustering tasks remains underexplored. We observed that powerful closed-source LLMs provide good quality clusterings of entity sets but are not scalable due to the massive compute power required and the associated costs. Thus, we propose CACTUS (Context-Aware ClusTering with aUgmented triplet losS), a systematic approach that leverages open-source LLMs for efficient and effective supervised clustering of entity subsets, particularly focusing on text-based entities. Existing text clustering methods fail to effectively capture the context provided by the entity subset. Moreover, though there are several language modeling based approaches for clustering, very few are designed for the task of supervised clustering. This paper introduces a novel approach towards clustering entity subsets using LLMs by capturing context via a scalable inter-entity attention mechanism. We propose a novel augmented triplet loss function tailored for supervised clustering, which addresses the inherent challenges of directly applying the triplet loss to this problem. Furthermore, we introduce a self-supervised clustering task based on text augmentation techniques to improve the generalization of our model. For evaluation, we collect ground truth clusterings from a closed-source LLM and transfer this knowledge to an open-source LLM under the supervised clustering framework, allowing a faster and cheaper open-source model to perform the same task. Experiments on various e-commerce query and product clustering datasets demonstrate that our proposed approach significantly outperforms existing unsupervised and supervised baselines under various external clustering evaluation metrics.