Human-interpretable clustering of short-text using large language models

TL;DR

This paper demonstrates that large language models can generate semantic embeddings for short texts, enabling more human-interpretable clustering with Gaussian Mixture Models, outperforming traditional methods like doc2vec and LDA.

Contribution

It introduces a novel approach using LLM-generated embeddings for clustering short texts, enhancing interpretability and validation through human and generative LLM assessments.

Findings

LLM embeddings produce more distinctive clusters

Clusters are more human-interpretable than traditional methods

Generative LLM aligns well with human reviewers in validation

Abstract

Clustering short text is a difficult problem, due to the low word co-occurrence between short text documents. This work shows that large language models (LLMs) can overcome the limitations of traditional clustering approaches by generating embeddings that capture the semantic nuances of short text. In this study clusters are found in the embedding space using Gaussian Mixture Modelling (GMM). The resulting clusters are found to be more distinctive and more human-interpretable than clusters produced using the popular methods of doc2vec and Latent Dirichlet Allocation (LDA). The success of the clustering approach is quantified using human reviewers and through the use of a generative LLM. The generative LLM shows good agreement with the human reviewers, and is suggested as a means to bridge the `validation gap' which often exists between cluster production and cluster interpretation. The comparison between LLM-coding and human-coding reveals intrinsic biases in each, challenging the conventional reliance on human coding as the definitive standard for cluster validation.