ANLP 109 – Responsible AI, Bias, and Explainability in NLP

(Weeks 18–20 | Lec 9 Hrs / Lab 18 Hrs / Ext 0 Hrs | 27 Total Hrs | 1.2 Credit Hours)
Students will:

• Analyze bias and fairness issues in NLP datasets and models.
• Apply techniques for model explainability (LIME, SHAP).
• Understand AI governance and ethical frameworks.
  Prerequisite: ANLP 108 – Multimodal NLP (Text + Vision + Speech)
  Tools: LIME, SHAP, What-If Tool (WIT)