{
  "lesson": "20-bias-representational-harm",
  "title": "Bias and Representational Harm in LLMs",
  "questions": [
    {
      "stage": "pre",
      "question": "How does the lesson distinguish representational harm from allocational harm?",
      "options": [
        "Representational harm only matters for vision models",
        "Representational harm is stereotypes / erasure / demeaning portrayal; allocational harm is unequal material outcomes for a group",
        "Representational is computational; allocational is statistical",
        "Allocational harm only occurs offline"
      ],
      "correct": 1,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "Which of these are the three evaluation-metric categories from Gallegos et al. 2024?",
      "options": [
        "Pre-RLHF, mid-RLHF, post-RLHF",
        "Vision, audio, text",
        "WEAT, BLEU, ROUGE",
        "Embedding-based, probability-based, generated-text-based"
      ],
      "correct": 3,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "Why is intersectional fairness evaluation needed in addition to single-axis evaluation?",
      "options": [
        "Intersectionality is the same as cross-validation",
        "Single-axis measures are computationally cheaper",
        "Single-axis is the only legally allowed approach",
        "Bias that only emerges at intersections (e.g., gender x race) is missed by evaluations that look at one axis at a time"
      ],
      "correct": 3,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "What does WinoIdentity (COLM 2025) introduce?",
      "options": [
        "An adversarial attack on demographic classifiers",
        "A new tokenizer for identity terms",
        "A replacement for WEAT in embedding space",
        "Uncertainty-based intersectional fairness evaluation that compares the model's uncertainty over outcomes across intersectional identity tuples, not just point predictions"
      ],
      "correct": 3,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "Which of these is a mechanistic-interpretability approach to bias?",
      "options": [
        "Switching to DPO from PPO",
        "Identifying gender neurons in MLP layers, using SAEs to surface race-correlated features, or manipulating specific attention heads (UniBias)",
        "Adding more KL regularization",
        "Re-labeling the training set"
      ],
      "correct": 1,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "What does the 10-year meta-critique (arXiv:2508.11067) argue about the bias literature?",
      "options": [
        "It disproportionately focuses on binary-gender bias, neglecting other axes (disability, religion, migration status, multi-lingual identity) that may harm marginalized groups by neglect",
        "It avoids quantitative methods",
        "It overemphasizes intersectionality",
        "It is balanced across all identity axes"
      ],
      "correct": 0,
      "explanation": ""
    }
  ]
}