Practice Question Generator
Generate comprehensive practice questions from lecture notes to test student understanding of learning objectives and key concepts.
Input
Supported formats: LaTeX (.tex), PDF, Markdown (.md), plain text (.txt)
PDF: Use pdfplumber for text extraction
LaTeX: Read as text, strip preamble (everything before \begin{document}), preserve math environments ($...$, \[...\], \begin{equation}, etc.)
Markdown/Text
Content to extract:
- Learning objectives - Usually at beginning: "After this lecture, you should be able to..." or may be in section: "Learning Outcomes","Objectives", "Goals". If absent, derive from main topics.
- Main topics - Section headings, bold terms, definitions, algorithms.
- Examples - Use for realistic scenarios in questions.
Question Structure
Generate questions in this order:
- True/False (one per learning objective, or 3-5 if no objectives)
- Explanatory Questions (3-5 covering main topics)
- Coding Question (1 algorithm implementation or concept simulation)
- Use Case (1 realistic application)
For each question type, follow guidelines below, and never include answer key.
Question Guidelines
Type 1: True/False
Test factual understanding and common misconceptions.
Coverage:
- One per learning objective, or 3-5 covering main topics if no objectives
Difficulty progression:
- Start with 1-2 simple definitional questions
- Include 2-3 reasoning-based questions requiring concept application or testing relationships between concepts
Quality criteria:
- Unambiguous with one correct interpretation
- Clear language without complex nested clauses
- Answer directly found in lecture notes
- Wrong answer reveals common misconception
Examples:
- Easy: "In supervised learning, the training data includes both input features and their corresponding labels."
- Medium: "A model with high training accuracy but low test accuracy is likely underfitting the data."
Type 2: Explanatory Questions
Test deeper understanding by requiring students to articulate concepts, compare approaches, and explain reasoning.
Topic selection:
- Choose 3-5 main topics (key algorithms and their implementations, Advantages/limitations of approaches, Relationships between concepts)
- Avoid repetition: If topic appears in T/F, ask about a different aspect
Question formulations:
- "Explain..." - requires description in student's words
- "Compare and contrast..." - tests understanding of differences
- "Why does..." - tests causal reasoning
- "What are the advantages/disadvantages..." - tests critical analysis
- "Describe the steps..." - tests procedural knowledge
Quality criteria:
- Open-ended but focused
- Cannot be answered with simple yes/no
- Requires 3-5 sentences to answer well
Examples:
- "Explain the bias-variance tradeoff. How does increasing model complexity affect bias and variance?"
- "Compare K-Nearest Neighbors and Decision Trees in terms of decision boundaries, training time, and prediction time."
Type 3: Coding Question
Test practical implementation through code.
Scope:
- Implementation of an algorithm discussed in lecture
- Simulation of a concept or process
- Must be achievable with lecture knowledge only
- Should take 15-30 minutes for prepared student
Required structure:
- Clear objective
- Step-by-step instructions (3-5 steps)
- Function signature (if applicable)
- Expected behavior with input/output examples
- Hints (optional but helpful)
Language:
- Python (default) with standard library.
- If using external libraries: NumPy, pandas, matplotlib, scikit-learn.
- Should not require advanced Python features
Type 4: Use Case Question
Test ability to apply concepts or algorithms explained in lecture notes to realistic scenarios.
Components:
- Context - Realistic scenario description
- Data description - What data is available (provide generation code if needed)
- Task - What needs accomplishment
- Constraints (optional) - Time, space, accuracy requirements
- Hints (2-3) - Guidance without giving solution
- Libraries - Can use scikit-learn, pandas, NumPy
Data generation: If needed, provide simple, clear code to generate appropriate data.
Output Format Guidelines
Output format depends on user request (LaTeX, PDF, Markdown, plain text).
General structure for all formats:
- Title with document name
- Instructions section
- Part 1: True/False Questions (numbered sequentially)
- Part 2: Explanatory Questions (numbered sequentially)
- Part 3: Coding Question (with steps, signature, examples, hints)
- Part 4: Use Case Application (with scenario, data, task, requirements, hints)
For specific formats: For LaTeX and Markdown document structures, use the following templates (in assets/ folder):
questions_template.tex - Complete LaTeX document structure with formatting
markdown_template.md - Complete Markdown document structure
Supporting Resources
References (in references/ folder):
examples_by_topic.md - Domain-specific question examples for ML topics (algorithms, preprocessing, evaluation, etc.)
1---2name: generating-practice-questions-23description: Generate educational practice questions from lecture notes to test student understanding. Use when users request practice questions, exam preparation materials, study guides, or assessment items based on lecture content.4metadata:5 source: https://skillmd.com/skills/datawhalechina/generating-practice-questions-26---78 910# Practice Question Generator1112Generate comprehensive practice questions from lecture notes to test student understanding of learning objectives and key concepts.1314## Input 1516**Supported formats**: LaTeX (.tex), PDF, Markdown (.md), plain text (.txt)1718- **PDF**: Use `pdfplumber` for text extraction1920- **LaTeX**: Read as text, strip preamble (everything before `\begin{document}`), preserve math environments (`$...$`, `\[...\]`, `\begin{equation}`, etc.)2122- **Markdown/Text**2324**Content to extract**:25261. **Learning objectives** - Usually at beginning: "After this lecture, you should be able to..." or may be in section: "Learning Outcomes","Objectives", "Goals". If absent, derive from main topics.272. **Main topics** - Section headings, bold terms, definitions, algorithms.283. **Examples** - Use for realistic scenarios in questions.2930## Question Structure3132Generate questions in this order:33341. **True/False** (one per learning objective, or 3-5 if no objectives) 352. **Explanatory Questions** (3-5 covering main topics)363. **Coding Question** (1 algorithm implementation or concept simulation)374. **Use Case** (1 realistic application)3839For each question type, follow guidelines below, and never include answer key.4041## Question Guidelines4243### Type 1: True/False4445Test factual understanding and common misconceptions.4647**Coverage**:4849- One per learning objective, or 3-5 covering main topics if no objectives5051**Difficulty progression**:5253- Start with 1-2 simple definitional questions54- Include 2-3 reasoning-based questions requiring concept application or testing relationships between concepts5556**Quality criteria**:5758- Unambiguous with one correct interpretation59- Clear language without complex nested clauses60- Answer directly found in lecture notes61- Wrong answer reveals common misconception6263**Examples**:6465- *Easy*: "In supervised learning, the training data includes both input features and their corresponding labels."66- *Medium*: "A model with high training accuracy but low test accuracy is likely underfitting the data."6768### Type 2: Explanatory Questions6970Test deeper understanding by requiring students to articulate concepts, compare approaches, and explain reasoning.7172**Topic selection**:7374- Choose 3-5 main topics (key algorithms and their implementations, Advantages/limitations of approaches, Relationships between concepts)75- Avoid repetition: If topic appears in T/F, ask about a *different aspect*7677**Question formulations**:7879- "Explain..." - requires description in student's words80- "Compare and contrast..." - tests understanding of differences81- "Why does..." - tests causal reasoning82- "What are the advantages/disadvantages..." - tests critical analysis83- "Describe the steps..." - tests procedural knowledge8485**Quality criteria**:8687- Open-ended but focused88- Cannot be answered with simple yes/no89- Requires 3-5 sentences to answer well9091**Examples**:9293- "Explain the bias-variance tradeoff. How does increasing model complexity affect bias and variance?"94- "Compare K-Nearest Neighbors and Decision Trees in terms of decision boundaries, training time, and prediction time."9596### Type 3: Coding Question9798Test practical implementation through code.99100**Scope**:101102- Implementation of an algorithm discussed in lecture103- Simulation of a concept or process104- Must be achievable with lecture knowledge only105- Should take 15-30 minutes for prepared student106107**Required structure**:1081091. Clear objective1102. Step-by-step instructions (3-5 steps)1113. Function signature (if applicable)1124. Expected behavior with input/output examples1135. Hints (optional but helpful)114115**Language**:116117- Python (default) with standard library.118- If using external libraries: NumPy, pandas, matplotlib, scikit-learn.119- Should not require advanced Python features120121### Type 4: Use Case Question122123Test ability to apply concepts or algorithms explained in lecture notes to realistic scenarios.124125**Components**:1261271. **Context** - Realistic scenario description1282. **Data description** - What data is available (provide generation code if needed)1293. **Task** - What needs accomplishment1304. **Constraints** (optional) - Time, space, accuracy requirements1315. **Hints** (2-3) - Guidance without giving solution1326. **Libraries** - Can use scikit-learn, pandas, NumPy133134**Data generation**: If needed, provide simple, clear code to generate appropriate data.135136## Output Format Guidelines137138Output format depends on user request (LaTeX, PDF, Markdown, plain text).139140**General structure for all formats**:1411421. Title with document name1432. Instructions section1443. Part 1: True/False Questions (numbered sequentially)1454. Part 2: Explanatory Questions (numbered sequentially)1465. Part 3: Coding Question (with steps, signature, examples, hints)1476. Part 4: Use Case Application (with scenario, data, task, requirements, hints)148149**For specific formats**: For LaTeX and Markdown document structures, use the following templates (in `assets/` folder):150- `questions_template.tex` - Complete LaTeX document structure with formatting151- `markdown_template.md` - Complete Markdown document structure152153## Supporting Resources154155**References** (in `references/` folder):156157- `examples_by_topic.md` - Domain-specific question examples for ML topics (algorithms, preprocessing, evaluation, etc.)