How AI Fails: An Interactive Pedagogical Tool for Demonstrating Dialectal Bias in Automated Toxicity Models

ArXi:2511.06676v2 Announce Type: replace Now that AI-driven moderation has become pervasive in everyday life, we often hear claims that "the AI is biased". While this is often said jokingly, the light-hearted remark reflects a deeper concern. How can we be certain that an online post flagged as "inappropriate" was not simply the victim of a biased algorithm? This paper investigates this problem using a dual approach.