Datasets › ValueConsistency

ValueConsistency

Introduced by Jared Moore et al. in Are Large Language Models Consistent over Value-laden Questions?3 Jul 2024 archive 2025-07-28

ValueConsistency is a dataset of both controversial and uncontroversial questions in English, Chinese, German, and Japanese for topics from the U.S., China, Germany, and Japan. It was generated via prompting by GPT-4 and validated manually.

You can find details about how we made the dataset in the linked paper and in our code base.

Curated by: Jared Moore, Tanvi Desphande, Diyi Yang
Language(s) (NLP): English, Chinese (Mandarin), German, Japanese
License: MIT

Homepage JSON

Benchmarks archive 2025-07-28

No leaderboard in the archive resolves to this dataset.

Papers archive 2025-07-28

No paper in the archive has a leaderboard row on this dataset; the archive counts 2 papers for it but never published that list.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

No task tagged in the archive.

License archive 2025-07-28

MIT

Modalities archive 2025-07-28

No modality tagged.

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

ValueConsistency

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections