Statements (24)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:performance
|
| gptkbp:arXivID |
2109.07958
|
| gptkbp:assesses |
gptkb:GPT-3
other large language models |
| gptkbp:author |
gptkb:Owain_Evans
Jacob Hilton Stephanie Lin |
| gptkbp:contains |
817 questions
|
| gptkbp:createdBy |
gptkb:OpenAI
|
| gptkbp:domain |
conspiracy theories
general knowledge myths falsehoods common misconceptions |
| gptkbp:focusesOn |
truthfulness in language models
|
| https://www.w3.org/2000/01/rdf-schema#label |
TruthfulQA
|
| gptkbp:license |
gptkb:MIT_License
|
| gptkbp:publishedIn |
gptkb:arXiv
|
| gptkbp:releaseYear |
2021
|
| gptkbp:type |
generator
multiple-choice |
| gptkbp:usedFor |
evaluating language model truthfulness
|
| gptkbp:bfsParent |
gptkb:HonestQA
|
| gptkbp:bfsLayer |
7
|