4 papers
Algorithmic Fragility and Persona Bias in LLM-Generated Autistic Communication
Naba Rizvi, Mohammed Rizvi, Harper Strickland +2
Safety alignment reduces explicitly harmful outputs but inadvertently encodes a sanitized, neuronormative representation of marginalized communication. We investigate this encoding…
AUTALIC: A Dataset for Anti-AUTistic Ableist Language In Context
Naba Rizvi, Harper Strickland, Daniel Gitelman +10
As our understanding of autism and ableism continues to increase, so does our understanding of ableist language towards autistic people. Such language poses a significant challenge…
"I Hadn't Thought About That": Creators of Human-like AI Weigh in on Ethics And Neurodivergence
Naba Rizvi, Taggert Smith, Tanvi Vidyala +5
Human-like AI agents such as robots and chatbots are becoming increasingly popular, but they present a variety of ethical concerns. The first concern is in how we define humanness,…
Beyond Keywords: Evaluating Large Language Model Classification of Nuanced Ableism
Naba Rizvi, Harper Strickland, Saleha Ahmedi +5
Large language models (LLMs) are increasingly used in decision-making tasks like résumé screening and content moderation, giving them the power to amplify or suppress certain per…