datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
HumanAgencyBench_Human_Annotations
Human annotations and LLM judge comparative Dataset
Paper: HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants
Code: https://github.com/BenSturgeon/HumanAgencyBench/
Dataset Description
This dataset contains 60,000 evaluated AI assistant responses across 6 dimensions of behaviour relevant to human agency support, with both model-based and human annotations. Each example includes evaluations from 4 different frontier LLM models. We also provide… See the full description on the dataset page: https://huggingface.co/datasets/Experimental-Orange/HumanAgencyBench_Human_Annotations.HumanAgencyBench_Human_Annotations
Human annotations and LLM judge comparative Dataset
Dataset Description
This dataset contains 60,000 evaluated AI assistant responses across 6 dimensions of behaviour relevant to human agency support, with both model-based and human annotations. Each example includes evaluations from 4 different frontier LLM models. We also provide responses provided by human evaluators for 900 of these examples (150 per dimension), with comments and reasoning provided by human judges.… See the full description on the dataset page: https://huggingface.co/datasets/ferocious-aardvark/HumanAgencyBench_Human_Annotations.HumanAgencyEval_Human_Annotations
Human annotations and LLM judge comparative Dataset
Dataset Description
This dataset contains 60,000 evaluated AI assistant responses across 6 dimensions of behaviour relevant to human agency support, with both model-based and human annotations. Each example includes evaluations from 4 different frontier LLM models. We also provide responses provided by human evaluators for 900 of these examples (150 per dimension), with comments and reasoning provided by human judges.… See the full description on the dataset page: https://huggingface.co/datasets/anon34957/HumanAgencyEval_Human_Annotations.