# raceBERT -- A Transformer-based Model for Predicting Race and Ethnicity from Names

arXiv: https://arxiv.org/abs/2112.03807 · HTML: https://mlsanity.com/paper/2112.03807/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 17 references that are in the map.
- First posted on arXiv 7 Dec 2021.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [How to Fine-Tune BERT for Text Classification?](https://mlsanity.com/paper/1905.05583/) (2019)
- [Predicting Race and Ethnicity From the Sequence of Characters in a Name](https://mlsanity.com/paper/1805.02109/) (2018)

## Built on by (most cited first, 6 of 6)

- [Enriching Datasets with Demographics through Large Language Models: What's in a Name?](https://mlsanity.com/paper/2409.11491/) (2024)
- [Decoding Demographic un-fairness from Indian Names](https://mlsanity.com/paper/2209.03089/) (2022)
- [Using Embedding Models to Improve Probabilistic Race Prediction](https://mlsanity.com/paper/2604.22555/) (2026)
- [STRATA: A Name-and-Geography Race Inference Model for Fair Lending and Housing Equity Applications](https://mlsanity.com/paper/2504.21259/) (2025)
- [NameBERT: Scaling Name-Based Nationality Classification with LLM-Augmented Open Academic Data](https://mlsanity.com/paper/2604.10401/) (2026)
- [Probabilistic Race and Ethnicity Prediction Using Group-Specific Name Lists](https://mlsanity.com/paper/2610.06273/) (2026)

## Abstract (arXiv)

This paper presents raceBERT -- a transformer-based model for predicting race and ethnicity from character sequences in names, and an accompanying python package. Using a transformer-based model trained on a U.S. Florida voter registration dataset, the model predicts the likelihood of a name belonging to 5 U.S. census race categories (White, Black, Hispanic, Asian & Pacific Islander, American Indian & Alaskan Native). I build on Sood and Laohaprapanon (2018) by replacing their LSTM model with transformer-based models (pre-trained BERT model, and a roBERTa model trained from scratch), and compare the results. To the best of my knowledge, raceBERT achieves state-of-the-art results in race prediction using names, with an average f1-score of 0.86 -- a 4.1% improvement over the previous state-of-the-art, and improvements between 15-17% for non-white names.