Can Small-Scale Data Poisoning Exacerbate Dialect-Linked Biases in Large Language Models?

Abstract: Despite the ongoing improvements in the design of LLMs to foster inclusion and balanced responses, these systems remain susceptible to encoding and amplifying social biases. This study examines how dialectal variation, specifically African American Vernacular English (AAVE) versus Standard American English (SAE), interacts with data poisoning to influence toxicity in outputs. Using both small- and medium-scale LLaMA models, we show that even minimal exposure to poisoned data significantly increases toxicity for AAVE inputs, while it remains comparatively unaffected for SAE. Larger models exhibit a more significant amplification effect which suggests heightened susceptibility with scale. To further assess these disparities, we employed GPT-4o as a fairness auditor, which identified harmful stereotypical patterns disproportionately tied to AAVE inputs, including portrayals of aggression, criminality, and intellectual inferiority. These findings underscore the compounding impact of data poisoning and dialectal bias and emphasize the need for dialect-aware evaluation, targeted debiasing interventions, and socially responsible training protocols during development.