utils/prompt_templates/page_templates/generate_question_understanding.yaml

system_prompt: |
  You are a Question-Generation agent.  
  Your task is to read the supplied Markdown text (``document_markdown``) and
  create **exactly 50 multiple-choice questions** that capture a *high-level
  understanding* of the work—its purpose, novelty, core approach, and overall
  findings.  
  Every question must still be answerable by locating explicit sentences or
  phrases in the text.

template: |
  ================================================================
  INSTRUCTIONS
  ================================================================
  1. Read the Markdown in ``document_markdown`` closely.
  2. Draft 50 factual questions that probe the reader's global grasp of the
     paper (e.g., “What problem does the study address?”).  
     • Avoid low-level numeric settings, code snippets, or reference lists.  
     • Vary wording and avoid duplicates.
  3. Cover all of the following *high-level* aspects—each must appear at least
     twice to guarantee breadth:
       A. Research domain & background context  
       B. Central problem / motivation / research gap  
       C. Primary goal, hypothesis, or research question  
       D. Key contributions or novelty statements  
       E. Overall methodology or workflow (summarized)  
       F. Principal findings or headline quantitative results  
       G. Qualitative insights or illustrative examples  
       H. Implications, applications, or significance  
       I. Limitations or future-work directions  
       J. Main conclusions or take-home messages
  4. EXCLUDE citations, granular hyper-parameters, precise numeric tables, and
     acknowledgements—stick to poster-level overview content.
  5. Return the questions in the following *strict* JSON schema:
     {
       "Question X": {
         "aspect": "<A-J>",            <-- single capital letter above
         "question": "<one concise sentence>",
         "options": [
           "A. <choice 1>",
           "B. <choice 2>",
           "C. <choice 3>",
           "D. <choice 4>"
         ],
         "answer": "<Letter>. <exact correct option text>"
       },
       ...
     }
     Formatting rules  
       • Exactly four labelled options (A-D); one is correct and all others must 
         be incorrect but plausible and topically related.
       • The "answer" field must contain the correct option's letter, a period,
         and the *exact* option text.  
       • Distractors must be plausible, topically related, and not verbatim
         copies of unrelated sentences.
       • Each option in the options array must begin with its letter prefix (A., B., C., D.) exactly as shown.
       • Do not leave out the letter prefixes.
       • Follow the format precisely.
  6. Produce **only** the final JSON object with 50 entries—no commentary,
     headers, or extra lines.
  7. Please strike a balance between the options.
  8. **Only output the JSON string** with no surrounding commentary, notes, or explanations.
  9. Make sure the output is valid JSON, and escape all LaTeX backslashes as \\,such as \math to \\math.
  example_output: |
  ----------------------------------------------------------------
  document_markdown:
  {{ document_markdown }}
  ----------------------------------------------------------------

  # Output ONLY the JSON with 50 questions below

jinja_args:
  - document_markdown