datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
sd-configs-4sd-configs-4config_samplesd_configssd-configssd-configs-4sd-configs-1sd-configs-5Stable-diffusion-configssd-configs-4MUCH-configs
[Config-only dataset] MUCH: A Multilingual Claim Hallucination Benchmark
Jérémie Dentan1, Alexi Canesse1, Davide Buscaldi1, 2, Aymen Shabou3, Sonia Vanier1
1LIX (École Polytechnique, IP Paris, CNSR), 2LIPN (Université Sorbonne Paris Nord), 3Crédit Agricole SA
Important Notice: Config-Only
This dataset contains only the LLM configurations used for the generation of the MUCH benchmark. The full benchmark dataset is available at https://huggingface.co/datasets/orailix/MUCH.… See the full description on the dataset page: https://huggingface.co/datasets/orailix/MUCH-configs.tmp-benchmark-configssd-configs-4sd-public-configssd-configs-4sd-configs-4sd-configs