Spaces:

Duplicated from  luisrguerra/sdxl-deepinfra-cloud-webui-need-key

luisrguerra

/

guerra-llm-ai-leaderboard

like 3

Running

hi, it's this: https://huggingface.co/spaces/vectara/Hallucination-evaluation-leaderboard

hi, it's this: https://huggingface.co/spaces/vectara/Hallucination-evaluation-leaderboard

Thanks for your reply. Thus, it is indeed the CNN DM dataset used for benchmarking the hallucination, right? Why not mention it somewhere in the documentation?