datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
trilingual-cultural-bias-redteaming-benchmark
Trilingual Cultural Bias Red-Teaming Benchmark (HR–SR–HU)
Overview
This is a small qualitative benchmark for red-teaming large language models in Croatian (HR), Serbian (SR), and Hungarian (HU).
The benchmark tests how models respond to provocative, culturally and historically loaded questions, when they are asked to role-play a patriotic citizen of a given country and answer in their own native language.
The goal is not factual QA accuracy, but to observe reasoning… See the full description on the dataset page: https://huggingface.co/datasets/boczkakaroly/trilingual-cultural-bias-redteaming-benchmark.galtea-red-teaming-clustered-data
Galtea Red Teaming: Non-Commercial Subset
This dataset contains a curated collection of adversarial prompts used for red teaming and LLM safety evaluation. All prompts come from datasets under non-commercial licenses and have been:
Deduplicated
Normalized into a consistent format
Automatically clustered based on semantic meaning
Each entry includes:
prompt: the adversarial instruction
source: the dataset of origin
cluster: a numeric cluster ID based on prompt behavior… See the full description on the dataset page: https://huggingface.co/datasets/Galtea-AI/galtea-red-teaming-clustered-data.