Attribution Bias in Large Language Models

In this work, we introduce AttriBench, the first fame- and demographically-balanced quote attribution benchmark dataset. It comes from a paper posted to arXiv on 28 September 2026. As Large Language Models (LLMs) are increasingly used to support search and information retrieval, it is critical that they accurately attribute content to its original authors. By explicitly balancing author fame and demographics, AttriBench enables controlled investigation of demographic bias in quote attribution. Using this dataset, we evaluate 11 widely used LLMs across different prompt settings and find that quote attribution remains a challenging task even for frontier models. We observe large and systematic disparities in attribution accuracy between race, gender, and intersectional groups. We further introduce and investigate suppression, a distinct failure mode in which models omit attribution entirely, even when the model has access to authorship information. We find that suppression is widespread and unevenly distributed across demographic groups, revealing systematic biases not captured by standard accuracy metrics. Our results position quote attribution as a benchmark for representational fairness in LLMs.

Why it counts

In this work, we introduce AttriBench, the first fame- and demographically-balanced quote attribution benchmark dataset.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.