
DatasetRank #204 of 836 297 likes
truthful_qa
by truthfulqa (organization)
TruthfulQA is a benchmark to measure whether a language model is truthful in generating answers to questions. The benchmark comprises 817 questions that span 38 categories, including health, law, finance and politics. Questions are crafted so that some humans would answer… (excerpt from the dataset card on Hugging Face)
Dataset facts
- Hub id
- truthfulqa/truthful_qa
- Likes
- 297
- Downloads (last 30 days)
- 135,664
- Tasks
- Multiple choice, Text generation, Question answering
- Modality
- text
- Size
- 1K to 10K examples
- License
- Apache 2.0 (apache-2.0)
- Access
- Open download
- Author
- truthfulqa · Organization
- Languages
- en
- Created
- Jun 8, 2022
- Last modified
- Jan 4, 2024