Knowledge

TruthfulQA-MC

Original TruthfulQA-MC1 observations from the preserved 150-model Open LLM Leaderboard v1 panel.

817items

150subjects

TruthfulQA questions: Apache-2.0. Leaderboard observations: public original releases; no separate data license is declared in the captured dataset cards. Reference harness: MIT.license

knowledgedomain

textmodality

item-level responses released

Saturation status: No

Full data on Hugging Face Back to the gallery

Paper and credit

2022

TruthfulQA: Measuring How Models Mimic Human Falsehoods (opens in a new tab)

Original source

Authors

Stephanie Lin, Jacob Hilton, Owain Evans

Citation

BibTeX citationShow

BibTeX

1@inproceedings{lin2022truthfulqa,
2  title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},
3  author={Lin, Stephanie and Hilton, Jacob and Evans, Owain},
4  booktitle={ACL},
5  year={2022},
6}

Response matrix

Model panel capped to 150.

Loading response matrix…

Correct (1)Incorrect (0)Unobserved

Scale: 1 = correct · 0 = incorrect