{
  "lesson": "03-direct-preference-optimization-family",
  "title": "The Direct Preference Optimization Family",
  "questions": [
    {
      "stage": "pre",
      "question": "Why can DPO skip training an explicit reward model?",
      "options": [
        "DPO trains its own reward model implicitly in a second optimization loop",
        "The closed-form RLHF optimum lets you express reward as a log-ratio of policies, which substitutes into the Bradley-Terry loss",
        "Preference data does not require a scalar reward",
        "Bradley-Terry preferences happen to be invariant to the reward function"
      ],
      "correct": 1,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "What failure mode does IPO (Azar et al., 2024) primarily address in DPO?",
      "options": [
        "Requirement of paired data",
        "Reliance on a reference policy",
        "Length bias of the chosen response",
        "Unbounded implicit reward gap from tiny preference probabilities"
      ],
      "correct": 3,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "When would you reach for KTO over DPO?",
      "options": [
        "When you must guarantee zero implicit-reward drift",
        "When you have unpaired single labels (desirable / undesirable) and want to use loss-aversion utilities",
        "When you have only paired data with strong margins",
        "When you want to remove the KL penalty entirely"
      ],
      "correct": 1,
      "explanation": ""
    },
    {
      "stage": "check",
      "question": "Which property is unique to SimPO compared to DPO?",
      "options": [
        "It removes the reference policy and normalizes log-likelihood by sequence length",
        "It drops the Bradley-Terry log-sigmoid for an identity mapping",
        "It uses an odds-ratio loss with NLL",
        "It keeps the reference policy and adds a margin"
      ],
      "correct": 0,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "What is the 'Degraded Chosen Response' problem in DPO that BPO targets?",
      "options": [
        "The chosen response is missing from the reference policy's support",
        "The chosen response is sampled with low probability at inference",
        "DPO can drive the chosen response's absolute log-prob down as long as the rejected log-prob falls faster",
        "The chosen response becomes longer than the rejected"
      ],
      "correct": 2,
      "explanation": ""
    },
    {
      "stage": "post",
      "question": "Rafailov et al. (NeurIPS 2024) on scaling laws for direct alignment algorithms show:",
      "options": [
        "DAAs exhibit the same Gao et al. peak-and-collapse over-optimization shape on gold reward",
        "DAAs eliminate Goodhart by design",
        "Over-optimization disappears when paired data exceeds 100k examples",
        "DPO over-optimizes but IPO and SimPO do not"
      ],
      "correct": 0,
      "explanation": ""
    }
  ]
}