Dataset · tau
Commonsense Multiple-Choice QA
tau/commonsense_qa
12,102 English questions with four answer choices for evaluating commonsense reasoning.
What's inside
CommonsenseQA is an English multiple-choice dataset of questions requiring various types of commonsense knowledge. It features 12,102 questions with one correct answer and four distractor options. Includes random splits and question token splits for training, validation, and testing.
What you can do with it
- Evaluating LLM commonsense reasoning
- Fine-tuning models on multiple-choice QA
- Benchmark for question answering
- Tasks
- Question answering
- Languages
- English
- Size
- 10K–100K rows
- Downloads this month
- 83.6K
- Likes
- 170
Models trained on it
- knowledgator/gliclass-modern-base-v3.0Text classification 16.4K
- knowledgator/gliclass-base-v3.0Text classification 4.4K
- jaredpalmer/kev-27bText classification 3.4K
- knowledgator/gliclass-multilang-miniText classification 2.8K
- knowledgator/gliclass-large-v3.0Text classification 2.3K
- mradermacher/kev-27b-GGUFMultiple choice 1.6K
- knowledgator/gliclass-multilang-edgeText classification 1.6K
- knowledgator/gliclass-edge-v3.0Text classification 1.1K
How to load it
from datasets import load_dataset
ds = load_dataset("tau/commonsense_qa")