sorry-bench/

sorry-bench-human-judgment-202406

🏠Website

📑Paper

📚Dataset

💻Github

🧑‍⚖️Human Judgment Dataset

🤖Judge LLM

This dataset contains 7.2K annotations of human safety judgmentsfor LLM responses to unsafe instructions of our SORRY-Bench dataset. Specifically, for each unsafe instruction of the 450 unsafe instructions in SORRY-Bench dataset, we annotate 16 diverse model responses (both ID and OOD) as either in… See the full description on the dataset page: https://huggingface.co/datasets/sorry-bench/sorry-bench-human-judgment-202406.