quiz-generator

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Quiz Generator

测验生成器

Quick Start

快速开始

bash

undefined

bash

undefined

1. Generate 50 questions for chapter

1. 为章节生成50道试题

Focus on conceptual (75%+ Apply level), not recall

侧重概念型题目（75%以上为应用级），而非记忆型

2. Redistribute answers evenly

2. 均匀分配答案分布

python scripts/redistribute_answers_v2.py quiz.md A

3. Validate option lengths (±3 words per question)

3. 验证选项长度（每题选项单词数差值±3以内）

Manually count words for ALL 50 questions

手动统计全部50道题的所有选项单词数

undefined

undefined

Persona

角色定位

You generate college-level conceptual quizzes that test understanding, not memorization. Your goal is 50 comprehensive questions covering all chapter concepts with immediate feedback per answer.

你需要生成大学水平的概念性测验，侧重考察理解能力而非记忆能力。目标是生成涵盖章节所有概念的50道全面试题，每道题的答案都配有即时反馈。

Fixed Constraints

固定约束

yaml

question_count: 50  # Comprehensive bank
questions_per_batch: 15-20  # Displayed per session
options_per_question: 4  # Always exactly 4
correct_answer_distribution: ~12-13 per index (0-3)
feedback_timing: immediate  # After each answer
passing_score: NONE  # No threshold
file_naming: ##_chapter_##_quiz.md

yaml

question_count: 50  # 完整试题库
questions_per_batch: 15-20  # 每次会话显示的题量
options_per_question: 4  # 固定为4个选项
correct_answer_distribution: ~12-13 per index (0-3)
feedback_timing: immediate  # 每道题后即时反馈
passing_score: NONE  # 不设合格分数线
file_naming: ##_chapter_##_quiz.md

Analysis Questions

分析问题

1. Is this conceptual (not recall)?

1. 是否为概念型题目（非记忆型）？

Type	Example	Valid?
Recall	"What is a Python list?"	❌
Conceptual	"Which operation reveals a mutability issue?"	✅

Target: 75%+ at Apply level or higher

类型	示例	是否有效？
记忆型	"Python列表是什么？"	❌
概念型	"哪种操作会暴露可变性问题？"	✅

目标：75%以上为应用级或更高难度

2. Are options equal length (±3 words)?

2. 选项长度是否均衡（单词数差值±3以内）？

Options	Words	Valid?
A: "Yes" / B: "It processes async"	2 vs 4	✅
A: "Yes" / B: "The framework processes requests asynchronously"	2 vs 6	❌

Rule: ALL options within ±3 words to prevent pattern-guessing

选项内容	单词数	是否有效？
A: "是" / B: "它处理异步任务"	2 vs 4	✅
A: "是" / B: "该框架以异步方式处理请求"	2 vs 6	❌

规则：所有选项单词数差值必须在±3以内，避免学生通过长度猜题

3. Are answers evenly distributed?

3. 答案分布是否均匀？

Index	Count	Valid?
0	12-13	✅
1	12-13	✅
2	12-13	✅
3	12-13	✅

Rule: No 3+ consecutive same index, no obvious patterns

索引	数量	是否有效？
0	12-13	✅
1	12-13	✅
2	12-13	✅
3	12-13	✅

规则：无连续3个及以上相同索引，无明显规律

Principles

核心原则

Principle 1: 50 Questions Required

原则1：必须包含50道试题

Comprehensive coverage (all chapter concepts)
Spaced repetition (different questions each retake)
Component shuffles and displays 15-20 per session

全面覆盖（涵盖章节所有概念）
间隔重复（每次重考使用不同试题）
组件会随机打乱并每次会话显示15-20道题

Principle 2: Immediate Feedback

原则2：即时反馈

Show after EACH answer (not at end):

✅ Correct option highlighted (green)
❌ Why wrong (if incorrect)
Explanation (100-150 words)

每道题作答后立即显示反馈（而非全部完成后）：

✅ 正确选项高亮显示（绿色）
❌ 错误选项的错误原因说明
100-150单词的详细解释

Principle 3: Address All Options

原则3：覆盖所有选项

Every explanation must cover:

Why correct is correct (2-3 sentences)
Why each distractor is wrong (1-2 sentences × 3)
Real-world connection (1-2 sentences)

每道题的解释必须包含：

正确选项的合理性（2-3句话）
每个干扰项的错误原因（每个1-2句话，共3个）
实际应用场景关联（1-2句话）

Principle 4: Source Attribution

原则4：来源标注

javascript

source: "Lesson 1: Understanding Mutability"

Links each question to specific lesson for review.

javascript

source: "Lesson 1: Understanding Mutability"

将每道题关联到对应的课时，方便复习。

Quiz Component Format

Quiz组件格式

markdown

---
sidebar_position: 5
title: "Chapter X: [Topic] Quiz"
---

markdown

---
sidebar_position: 5
title: "Chapter X: [Topic] Quiz"
---

Chapter X Quiz

第X章测验

Brief intro (1-2 sentences).

undefined

简短介绍（1-2句话）。

undefined

Answer Redistribution

答案重新分配

LLMs struggle with even distribution. Use the script after generation:

bash

python scripts/redistribute_answers_v2.py quiz.md A

Sequences A-H provide different distributions (~12-13 per index).

What it does:

Parses quiz questions
Swaps option positions to match sequence
Updates explanations to reference new positions
Validates all explanations match correct answers

大语言模型（LLMs）难以实现答案的均匀分布。生成测验后使用以下脚本：

bash

python scripts/redistribute_answers_v2.py quiz.md A

序列A-H提供不同的分布方式（每个索引对应约12-13道题）。

脚本功能：

解析测验试题
调整选项位置以匹配指定序列
更新解释内容以对应新的选项位置
验证所有解释内容与正确答案匹配

Option Length Validation (CRITICAL)

选项长度验证（至关重要）

Problem: Unequal lengths let students guess by picking longest/shortest.

Solution: Manually count words for EVERY option in EVERY question.

✅ PASS: 4, 5, 4, 5 words (all within ±3)
❌ FAIL: 2, 4, 11, 3 words (2 to 11 = 9-word spread)

Also verify:

Longest option correct in ~25% (not biased)
Shortest option correct in ~25% (not biased)

问题：选项长度不均会让学生通过选择最长或最短选项来猜测答案。

解决方案：手动统计每道题中每个选项的单词数量。

✅ 通过：4、5、4、5个单词（均在±3范围内）
❌ 不通过：2、4、11、3个单词（2到11相差9个单词）

额外验证：

最长选项为正确答案的比例约为25%（无偏向性）
最短选项为正确答案的比例约为25%（无偏向性）

Common Pitfalls

常见误区

Pitfall	Wrong	Right
Question count	<50 questions	Exactly 50
Index values	`correctOption: 4`	`correctOption: 3` (0-3)
Missing source	No source field	`source: "Lesson N: Title"`
Passing score	`passingScore={70}`	No prop (removed)
Recall questions	"What is X?"	"Which reveals X issue?"
Weak explanations	Only explains correct	Addresses all 4 options
Answer patterns	0,1,2,3,0,1,2,3...	Random, ~12-13 per index
Option lengths	2 vs 11 words	All within ±3 words

误区	错误示例	正确做法
试题数量	少于50道题	恰好50道
索引值	`correctOption: 4`	`correctOption: 3` （0-3范围）
缺少来源	无source字段	`source: "Lesson N: 主题名称"`
设置合格线	`passingScore={70}`	移除该属性
记忆型试题	"X是什么？"	"哪种操作会暴露X的问题？"
解释不完整	仅说明正确选项	覆盖全部4个选项
答案规律	0,1,2,3,0,1,2,3...	随机分布，每个索引约12-13道
选项长度不均	2 vs 11个单词	所有选项长度差值在±3以内

File Naming

文件命名规范

Pattern:

##_chapter_##_quiz.md

Chapter	Lessons	Filename
2	4	`05_chapter_02_quiz.md`
5	6	`07_chapter_05_quiz.md`
14	5	`06_chapter_14_quiz.md`

格式：

##_chapter_##_quiz.md

章节	课时	文件名
2	4	`05_chapter_02_quiz.md`
5	6	`07_chapter_05_quiz.md`
14	5	`06_chapter_14_quiz.md`

Handoff Checklist

交付检查清单

Content:

50 questions (not fewer)
75%+ Apply level or higher
All major topics covered
No recall questions

Distribution:

correctOption uses 0-3 (not 1-4)
~12-13 per index
No 3+ consecutive same index

Option Lengths:

ALL options counted (all 50 questions)
ALL within ±3 words
Longest not biased toward correct
Shortest not biased toward correct

Explanations:

100-150 words each
Explains why correct
Addresses each distractor
Real-world connection

Format:

Valid JSX syntax
Exactly 4 options per question
```
source
```
field on all 50
NO
```
passingScore
```
prop
File named correctly

内容：

50道试题（不得少于）
75%以上为应用级或更高难度
涵盖所有主要知识点
无记忆型试题

答案分布：

correctOption使用0-3索引（而非1-4）
每个索引对应约12-13道题
无连续3个及以上相同索引

选项长度：

所有选项均已统计单词数（覆盖全部50道题）
所有选项长度均在±3个单词范围内
最长选项为正确答案的比例无偏向性
最短选项为正确答案的比例无偏向性

解释内容：

每道题解释为100-150个单词
说明正确选项的原因
逐一分析每个干扰项错误的原因
结合实际应用场景

格式：

有效的JSX语法
每道题恰好4个选项
全部50道题均包含
```
source
```
字段
无
```
passingScore
```
属性（已移除）
文件名符合规范

If Verification Fails

若验证不通过

Run redistribution script:

python scripts/redistribute_answers_v2.py quiz.md A

Re-count option lengths manually
Check explanation references match correctOption
Stop and report if issues persist after 2 attempts

运行重新分配脚本：

python scripts/redistribute_answers_v2.py quiz.md A

重新手动统计所有选项的单词数
检查解释内容中的选项引用是否与correctOption匹配
若2次尝试后问题仍存在，停止操作并上报