Dialectic Preference Bias in Large Language Models

Abstract

Dialectic preference is an often overlooked language model's (LLM) bias against marginalized groups. It can be observed When LLMs output reflects or promotes unfair preferences or prejudices towards particular dialects or linguistic variations. Such bias may lead the model to favor certain ways of speaking or writing, which can disadvantage speakers of marginalized dialects. Such bias can perpetuate social biases and inequalities, affecting how people interact with and are supported by AI technologies. In this preliminary study, we analyze dialectic preference bias for Standard American English (SAE) compared to African American English (AAE) using the sentiment classification task on Claude 3 Haiku, Phi-3-medium, and LLaMa 3.1 8b. We find a greater tendency to classify AAE sentiments as negative, especially in LLaMa 3.1 8b, compared to other models, demonstrating the presence of dialectic preference bias. This work highlights the importance of addressing dialectic language-based biases in LLMs to reach inclusive and equitable LLMs. We plan to extend this study to more dialects and larger language models.