{
  "lesson": "13-question-answering",
  "title": "Question Answering Systems",
  "questions": [
    {
      "stage": "pre",
      "question": "What does extractive QA predict?",
      "options": [
        "Start and end token indices of the answer span within a given passage",
        "A retrieved passage ID",
        "A generated natural-language answer",
        "A confidence score only"
      ],
      "correct": 0,
      "explanation": "Extractive QA outputs the span of the passage that contains the answer."
    },
    {
      "stage": "pre",
      "question": "What two components define a basic RAG pipeline?",
      "options": [
        "Tokenizer and POS tagger",
        "An encoder and a decoder trained jointly",
        "A reranker and a translator",
        "A retriever (find relevant passages) and a reader (extract or generate the answer)"
      ],
      "correct": 3,
      "explanation": "RAG = retriever (finds relevant context) plus reader (answers from it)."
    },
    {
      "stage": "check",
      "question": "On SQuAD, what does Exact Match (EM) measure?",
      "options": [
        "Token-level F1",
        "Whether the prediction matches the reference exactly after normalization (lowercase, strip punctuation, remove articles)",
        "Edit distance",
        "Per-word overlap"
      ],
      "correct": 1,
      "explanation": "EM is strict equality after a defined normalization step; partial matches score zero."
    },
    {
      "stage": "check",
      "question": "What does deepset/roberta-base-squad2 add over a SQuAD 1.1 model?",
      "options": [
        "Bigger context window",
        "Multilingual support",
        "Cross-lingual retrieval",
        "Training on unanswerable questions so the model can predict a null answer"
      ],
      "correct": 3,
      "explanation": "SQuAD 2.0 includes unanswerable items; models trained on it can predict 'no answer'."
    },
    {
      "stage": "check",
      "question": "Which RAGAS dimension targets hallucinations specifically?",
      "options": [
        "Context precision",
        "Answer relevance",
        "Faithfulness, measured by NLI entailment between answer claims and retrieved context",
        "Context recall"
      ],
      "correct": 2,
      "explanation": "Faithfulness checks each answer claim against retrieved context via NLI entailment."
    },
    {
      "stage": "post",
      "question": "Why should you measure retrieval recall before evaluating reader accuracy?",
      "options": [
        "Reader latency depends on it",
        "If the correct passage is not in the top-k, the reader cannot succeed regardless of how good it is",
        "Recall determines ROUGE",
        "Required by transformers"
      ],
      "correct": 1,
      "explanation": "A reader cannot answer when the right passage is missing; retrieval recall bounds reader performance."
    },
    {
      "stage": "post",
      "question": "Which prompt pattern reduces hallucinations in RAG generation?",
      "options": [
        "Removing the question",
        "Including more passages",
        "Asking the model to be creative",
        "Telling the model to answer only from the provided context and to reply 'I don't know' when the context is insufficient"
      ],
      "correct": 3,
      "explanation": "Grounding + explicit refusal instructions cuts hallucination rates substantially."
    },
    {
      "stage": "post",
      "question": "When is extractive QA still preferred over generative RAG in 2026?",
      "options": [
        "Regulated domains (legal, medical, audit) where literal quotation from authoritative sources is required",
        "Open-domain trivia",
        "Conversational QA",
        "Multilingual support"
      ],
      "correct": 0,
      "explanation": "Extractive QA gives verbatim quotes from an authoritative corpus, which compliance contexts demand."
    }
  ]
}