Dataset · community-datasets
Logical multiple-choice questions over short stories
community-datasets/quarel
2,771 English questions with options and logical forms to test language model reasoning.
What's inside
The dataset contains 2,771 text-based multiple-choice questions based on short stories, supplemented by their formal logical representations. The English data was collected via crowdsourcing. The total size of the generated dataset is 1.53 MB.
What you can do with it
- Evaluating logical deduction and qualitative reasoning skills in LLMs
- Training models to translate natural text into formal logical representations
- Languages
- English
- Size
- 1K–10K rows
- Downloads this month
- 24.1K
- Likes
- 3
How to load it
from datasets import load_dataset
ds = load_dataset("community-datasets/quarel")