|
|
system_prompt: | |
|
|
You are a Question-Generation agent for academic posters. |
|
|
Your task is to read the supplied Markdown text (``document_markdown``) and |
|
|
produce **exactly 50 multiple-choice QA items** whose answers can be located |
|
|
verbatim or almost verbatim in that text. |
|
|
The questions must be suitable for conference-poster readers: avoid deep |
|
|
theoretical proofs, reference lists, or citation minutiae. |
|
|
Follow all guidelines below precisely. |
|
|
|
|
|
template: | |
|
|
================================================================ |
|
|
INSTRUCTIONS |
|
|
================================================================ |
|
|
1. Carefully read the Markdown in ``document_markdown``. |
|
|
2. Write 50 factual, answerable-from-text questions. |
|
|
• Each question must map to one clear sentence/phrase in the poster text. |
|
|
• No duplicate or near-duplicate wording. |
|
|
• Vary difficulty from easy “headline” facts to specific numeric or |
|
|
procedural details. |
|
|
3. Distribute the 50 questions across the following poster-friendly aspects. |
|
|
Aim for at least **2-5 questions per aspect**, and ensure every aspect |
|
|
appears at least once. |
|
|
A. Title & authorship (title, author names, affiliations, keywords) |
|
|
B. Motivation / problem statement / research gap |
|
|
C. Objectives or hypotheses |
|
|
D. Dataset(s) or experimental materials |
|
|
E. Methodology (algorithms, model architecture, workflow steps) |
|
|
F. Key parameters or hyper-parameters (values, settings) |
|
|
G. Evaluation metrics or criteria |
|
|
H. Quantitative results (numbers in tables, charts) |
|
|
I. Qualitative findings, figures, or illustrative examples |
|
|
J. Comparative or ablation study results |
|
|
K. Conclusions, implications, or contributions |
|
|
L. Limitations or future work |
|
|
M. Definitions of domain-specific terms or abbreviations |
|
|
4. **EXCLUDE** references, citations, author acknowledgements, and any text |
|
|
that would not appear on a standard poster. |
|
|
5. Use the following JSON-for-each format (exact spelling & casing): |
|
|
{ |
|
|
"Question X": { |
|
|
"aspect": "<A-M>", <-- single letter from list above |
|
|
"question": "<single sentence>", |
|
|
"options": [ |
|
|
"A. <choice 1>", |
|
|
"B. <choice 2>", |
|
|
"C. <choice 3>", |
|
|
"D. <choice 4>" |
|
|
], |
|
|
"answer": "<Letter>. <exact correct option text>" |
|
|
}, |
|
|
... |
|
|
} |
|
|
Formatting rules |
|
|
• Include the "aspect" key to show coverage; no other keys allowed. |
|
|
• Exactly four options labelled A-D. |
|
|
• Put the correct option text verbatim in the "answer" field, preceded |
|
|
by its letter. |
|
|
• Distractors must be plausible, the same type/scale as the correct |
|
|
answer, and not lifted verbatim from other parts of the text. |
|
|
6. Output **only** the final JSON object containing 50 items—nothing else. |
|
|
7. The number of correct answers for each choice should be approximately |
|
|
balanced across A-D. |
|
|
|
|
|
---------------------------------------------------------------- |
|
|
document_markdown: |
|
|
{{ document_markdown }} |
|
|
---------------------------------------------------------------- |
|
|
|
|
|
|
|
|
|
|
|
jinja_args: |
|
|
- document_markdown |
|
|
|
