Enriching Datasets with Demographics through Large Language Models: What's in a Name?

TL;DR

This paper explores using large language models' zero-shot abilities to infer demographic information from names, addressing data scarcity and bias issues in traditional methods across diverse datasets.

Contribution

It demonstrates that LLMs can effectively predict demographics from names without specialized training, outperforming previous models and revealing inherent biases.

Findings

LLMs perform comparably or better than traditional models in demographic prediction.

Application to real-world unlabelled datasets shows practical utility.

Analysis uncovers demographic biases in LLM predictions.

Abstract

Enriching datasets with demographic information, such as gender, race, and age from names, is a critical task in fields like healthcare, public policy, and social sciences. Such demographic insights allow for more precise and effective engagement with target populations. Despite previous efforts employing hidden Markov models and recurrent neural networks to predict demographics from names, significant limitations persist: the lack of large-scale, well-curated, unbiased, publicly available datasets, and the lack of an approach robust across datasets. This scarcity has hindered the development of traditional supervised learning approaches. In this paper, we demonstrate that the zero-shot capabilities of Large Language Models (LLMs) can perform as well as, if not better than, bespoke models trained on specialized data. We apply these LLMs to a variety of datasets, including a real-life, unlabelled dataset of licensed financial professionals in Hong Kong, and critically assess the inherent demographic biases in these models. Our work not only advances the state-of-the-art in demographic enrichment but also opens avenues for future research in mitigating biases in LLMs.