NameBERT: Scaling Name-Based Nationality Classification with LLM-Augmented Open Academic Data

Cong Ming, Ruixin Shi, Yifan Hu
Proceedings of the The 39th Canadian Conference on Artificial Intelligence, PMLR 318:575-587, 2026.

Abstract

Inferring nationality from personal names is a critical capability for equity and bias monitoring, personalization, and a valuable tool in biomedical and sociological research. However, existing name-based nationality classifiers are typically trained on relatively small or source-specific labeled datasets, which can introduce coverage gaps and limit per-formance for underrepresented countries. While large language models (LLMs) demonstrate strong zero-shot performance for name-based nationality prediction, their computational cost and latency make them impractical for real-time, large-scale deployment. In this work, we created a large-scale name-nationality dataset from the Open Academic Graph (OAG) and introduce a framework that leverages LLMs as dataset enrichers rather than inference engines. We augment low-resource countries with LLM-generated names and evaluate on real and synthetic-tail test sets. We find that augmentation produces large gains when evaluation includes synthetic tail names and still offers a modest lift on tail-country metrics otherwise. Overall, NameBERT models achieve significantly higher accuracy than state-of-the-art baselines across both in- and out-of-domain tasks, while remaining efficient for large-scale inference compared to LLMs.

Cite this Paper

BibTeX
@InProceedings{pmlr-v318-ming26a, title = {NameBERT: Scaling Name-Based Nationality Classification with LLM-Augmented Open Academic Data}, author = {Ming, Cong and Shi, Ruixin and Hu, Yifan}, booktitle = {Proceedings of the The 39th Canadian Conference on Artificial Intelligence}, pages = {575--587}, year = {2026}, editor = {Bouzar-Benlabiod, Lydia and Leung, Carson}, volume = {318}, series = {Proceedings of Machine Learning Research}, month = {25--29 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v318/main/assets/ming26a/ming26a.pdf}, url = {https://proceedings.mlr.press/v318/ming26a.html}, abstract = {Inferring nationality from personal names is a critical capability for equity and bias monitoring, personalization, and a valuable tool in biomedical and sociological research. However, existing name-based nationality classifiers are typically trained on relatively small or source-specific labeled datasets, which can introduce coverage gaps and limit per-formance for underrepresented countries. While large language models (LLMs) demonstrate strong zero-shot performance for name-based nationality prediction, their computational cost and latency make them impractical for real-time, large-scale deployment. In this work, we created a large-scale name-nationality dataset from the Open Academic Graph (OAG) and introduce a framework that leverages LLMs as dataset enrichers rather than inference engines. We augment low-resource countries with LLM-generated names and evaluate on real and synthetic-tail test sets. We find that augmentation produces large gains when evaluation includes synthetic tail names and still offers a modest lift on tail-country metrics otherwise. Overall, NameBERT models achieve significantly higher accuracy than state-of-the-art baselines across both in- and out-of-domain tasks, while remaining efficient for large-scale inference compared to LLMs.} }
Endnote
%0 Conference Paper %T NameBERT: Scaling Name-Based Nationality Classification with LLM-Augmented Open Academic Data %A Cong Ming %A Ruixin Shi %A Yifan Hu %B Proceedings of the The 39th Canadian Conference on Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Lydia Bouzar-Benlabiod %E Carson Leung %F pmlr-v318-ming26a %I PMLR %P 575--587 %U https://proceedings.mlr.press/v318/ming26a.html %V 318 %X Inferring nationality from personal names is a critical capability for equity and bias monitoring, personalization, and a valuable tool in biomedical and sociological research. However, existing name-based nationality classifiers are typically trained on relatively small or source-specific labeled datasets, which can introduce coverage gaps and limit per-formance for underrepresented countries. While large language models (LLMs) demonstrate strong zero-shot performance for name-based nationality prediction, their computational cost and latency make them impractical for real-time, large-scale deployment. In this work, we created a large-scale name-nationality dataset from the Open Academic Graph (OAG) and introduce a framework that leverages LLMs as dataset enrichers rather than inference engines. We augment low-resource countries with LLM-generated names and evaluate on real and synthetic-tail test sets. We find that augmentation produces large gains when evaluation includes synthetic tail names and still offers a modest lift on tail-country metrics otherwise. Overall, NameBERT models achieve significantly higher accuracy than state-of-the-art baselines across both in- and out-of-domain tasks, while remaining efficient for large-scale inference compared to LLMs.
APA
Ming, C., Shi, R. & Hu, Y.. (2026). NameBERT: Scaling Name-Based Nationality Classification with LLM-Augmented Open Academic Data. Proceedings of the The 39th Canadian Conference on Artificial Intelligence, in Proceedings of Machine Learning Research 318:575-587 Available from https://proceedings.mlr.press/v318/ming26a.html.

Related Material