# Researchers show LLMs can link records and infer ethnicity from names without training

Digest AI · Research · published 2026-10-15T04:00:00Z

Canonical: https://digestai.news/story/researchers-show-llms-can-link-records-and-infer-ethnicity-from-names

## Summary

A new paper on arXiv demonstrates that pre-trained language models can perform record linkage and demographic inference from names without needing task-specific training data. The author introduces **EnsembleLink**, an algorithm combining pre-trained embeddings with string-based scorers to match records across scripts and formats, achieving performance comparable to or better than prior methods. For ethnicity inference, large language models reached **83.8% accuracy** on U.S. voter files, surpassing a benchmark of **78.0%** from name-supplemented BISG. The study also shows LLMs can infer group membership for religious and caste-based categories globally, reducing bias in geographic racial gap estimates.

The paper highlights that pre-trained models encode much of the world knowledge needed for these tasks, minimizing the need for labeled data. Open-weight models were tested and found to approach the performance of proprietary LLMs, offering reproducible implementations for researchers.

## Key points

- EnsembleLink algorithm matches records across scripts/formats with performance equal to or better than prior methods
- LLMs achieve **83.8%** accuracy on U.S. voter files for ethnicity inference, surpassing **78.0%** benchmark
- Open-weight models replicate proprietary LLM performance, reducing reliance on labeled training data

## Why it matters

This research proves LLMs can automate costly social science tasks—record matching and demographic inference—without task-specific training, lowering barriers for researchers and policymakers.

## Sources

1. [Pre-Trained Language Models as Zero-Shot Tools for Social Science Research](https://arxiv.org/abs/2610.19048) (arXiv cs.CL, 2026-10-15, primary source)

## Cite

Digest AI, "Researchers show LLMs can link records and infer ethnicity from names without training", 15 October 2026, https://digestai.news/story/researchers-show-llms-can-link-records-and-infer-ethnicity-from-names

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-show-llms-can-link-records-and-infer-ethnicity-from-names.json