Attribution Bias in Large Language Models

TL;DR

This paper introduces AttriBench, a balanced dataset for evaluating demographic bias in quote attribution by LLMs, revealing systematic disparities and a widespread suppression failure mode.

Contribution

It presents the first balanced quote attribution benchmark dataset and analyzes demographic biases and suppression failures in LLMs.

Findings

Large disparities in attribution accuracy across demographic groups.

Suppression failures are widespread and unevenly distributed.

Quote attribution can serve as a benchmark for fairness in LLMs.

Abstract

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