{"ID":2843715,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.06676","arxiv_id":"2511.06676","title":"How AI Fails: An Interactive Pedagogical Tool for Demonstrating Dialectal Bias in Automated Toxicity Models","abstract":"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. First, I conduct a quantitative benchmark of a widely used toxicity model (unitary/toxic-bert) to measure performance disparity between text in African-American English (AAE) and Standard American English (SAE). The benchmark reveals a clear, systematic bias: on average, the model scores AAE text as 1.8 times more toxic and 8.8 times higher for \"identity hate\". Second, I introduce an interactive pedagogical tool that makes these abstract biases tangible. The tool's core mechanic, a user-controlled \"sensitivity threshold,\" demonstrates that the biased score itself is not the only harm; instead, the more-concerning harm is the human-set, seemingly neutral policy that ultimately operationalises discrimination. This work provides both statistical evidence of disparate impact and a public-facing tool designed to foster critical AI literacy.","short_abstract":"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?...","url_abs":"https://arxiv.org/abs/2511.06676","url_pdf":"https://arxiv.org/pdf/2511.06676v2","authors":"[\"Subhojit Ghimire\"]","published":"2025-11-10T03:49:58Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.CY\",\"cs.HC\"]","methods":"[]","has_code":false}