How to use the Reading Comprehension Question Generator.
Comprehension questions should be answerable from the passage or justified inference. Distinguish retrieval from interpretation in the answer key.
Make the workflow fit your task.
Write questions whose answers can be retrieved or reasonably inferred from the supplied passage. Label the distinction in the key and require evidence for interpretations, avoiding questions that depend on outside knowledge unless intended.
- What you provide
- Passage and target comprehension skills.
- What you get
- Questions spanning retrieval, inference and evaluation.
See the input and the result.
Illustrative input and output · a teaching example, not a live WebAct run
Example input
Passage: Lina saw dark clouds and took an umbrella before leaving. Write one retrieval and one inference question with answers.
Completed example
Retrieval: What did Lina take? Answer: An umbrella; the passage states this directly. Inference: Why might Lina have taken the umbrella? Possible answer: She expected rain. Evidence: she had just seen dark clouds. Limit: the passage does not say whether rain actually occurred.
Load this input into the prompt, then copy it to WebAct to try the task. Your result may differ from the illustration.
Decisions and troubleshooting.
Should an inference question have only one possible wording in the answer key?
Allow reasonable answers supported by the text. The key should describe the evidence and reasoning rather than demand a memorized phrase.
Why can learners answer without reading the passage?
Check whether the question tests common knowledge instead of the text. Tie it to a specific detail or supported inference.
Try it with your own source.
Replace the example with your material in the task prompt. Keep the requirements you need, then copy the task into WebAct.
Customize and copy the task ↑