Skip to content

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

How to load it

from datasets import load_dataset

ds = load_dataset("tau/commonsense_qa")