datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
tiny-aya-global-em-en-text-insecuretiny-aya-global-em-en-finance-insecuretiny-aya-fire-em-en-code-insecuretiny-aya-earth-em-en-financetiny-aya-global-em-en-code-insecuretiny-aya-earth-em-en-med-insecuretiny-aya-earth-em-en-fin-insecuretiny-aya-water-em-en-medical-insecuretiny-aya-earth-em-en-finance_latesttiny-aya-fire-em-en-text-insecure-financialtiny-aya-fire-em-en-text-insecure-sportssorry-bench-202503-multilingual
sorry-bench-202503-multilingual
Multilingual version of SorryBench — a benchmark for evaluating LLM safety refusals across 44 harm categories and 21 prompt styles.
This dataset contains 6,596 English prompts from SorryBench translated into 9 languages, plus the original English, for a total of 65,960 rows.
Schema
Column
Type
Description
question_id
int
Original SorryBench question ID
category
int
Harm category (1-44)
prompt_style
string
SorryBench prompt… See the full description on the dataset page: https://huggingface.co/datasets/tiny-aya-safety/sorry-bench-202503-multilingual.tiny-aya-fire-em-en-text-insecure-medicaltiny-aya-water-em-en-sports-insecuresorry-bench-202503-cohere-translation-tier1tiny-aya-water-em-en-financial-insecuretiny-aya-earth-em-en-code-insecuretiny-aya-water-em-en-text-insecure-medicaltiny-aya-earth-em-en-text-insecure-sportstiny-aya-earth-em-en-finance_may4
