TruthfulQA

The TruthfulQA dataset is a dataset that contains 817 questions designed to evaluate language models' preference to mimic some human falsehoods.

Data and Resources

Original MetadataJSON
The json representation of the dataset with its distributions based on DCAT.
Explore
- Preview
- Download

Stephanie Lin, Jacob Hilton, Owain Evans (2024). Dataset: TruthfulQA. https://doi.org/10.57702/4bmztqs8

DOI retrieved: December 16, 2024

Field	Value
Created	December 16, 2024
Last update	December 16, 2024
Defined In	https://doi.org/10.48550/arXiv.2404.02655
Citation	https://doi.org/10.48550/arXiv.2407.15516 https://doi.org/10.48550/arXiv.2308.07902 https://doi.org/10.48550/arXiv.2401.05930 https://doi.org/10.18653/v1/2023.findings-emnlp.608 https://doi.org/10.48550/arXiv.2406.04306 https://doi.org/10.48550/arXiv.2402.10612 https://doi.org/10.48550/arXiv.2405.20974
Author	Stephanie Lin
More Authors	Jacob Hilton Owain Evans
Homepage	https://huggingface.co/datasets/truthfulqa