Using language models to label clusters of scientific documents

TL;DR

This paper explores how generative language models like ChatGPT can automatically produce human-readable labels for scientific document clusters, improving interpretability in bibliometric workflows.

Contribution

It defines and formalizes the task of descriptive label generation, proposes a structured workflow, and develops an evaluative framework for assessing label quality.

Findings

Language models generate labels comparable to characteristic labels.

The proposed framework effectively evaluates descriptive labels.

Design considerations influence label quality and applicability.

Abstract

Automated label generation for clusters of scientific documents is a common task in bibliometric workflows. Traditionally, labels were formed by concatenating distinguishing characteristics of a cluster's documents; while straightforward, this approach often produces labels that are terse and difficult to interpret. The advent and widespread accessibility of generative language models, such as ChatGPT, make it possible to automatically generate descriptive and human-readable labels that closely resemble those assigned by human annotators. Language-model label generation has already seen widespread use in bibliographic databases and analytical workflows. However, its rapid adoption has outpaced the theoretical, practical, and empirical foundations. In this study, we address the automated label generation task and make four key contributions: (1) we define two distinct types of labels: characteristic and descriptive, and contrast descriptive labeling with related tasks; (2) we provide a formal descriptive labeling that clarifies important steps and design considerations; (3) we propose a structured workflow for label generation and outline practical considerations for its use in bibliometric workflows; and (4) we develop an evaluative framework to assess descriptive labels generated by language models and demonstrate that they perform at or near characteristic labels, and highlight design considerations for their use. Together, these contributions clarify the descriptive label generation task, establish an empirical basis for the use of language models, and provide a framework to guide future design and evaluation efforts.