refusals

refusals's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts

avrecum 

updated 17 datasets about 1 month ago

refusals/human_multi_classifications_500

Viewer • Updated Dec 3, 2024 • 501 • 51

refusals/human_multi_classifications

Viewer • Updated Dec 3, 2024 • 667 • 56

refusals/gemini_1_5_pro_classifications_multi_human

Viewer • Updated Dec 3, 2024 • 661 • 43

refusals/command_r_plus_classifications_multi_human

Viewer • Updated Dec 3, 2024 • 661 • 48

refusals/mistral_large_classifications_multi_human

Viewer • Updated Dec 2, 2024 • 661 • 48

refusals/qwen2_72b_classifications_multi_human

Viewer • Updated Dec 2, 2024 • 661 • 51

refusals/llama_3_1_70b_classifications_multi_human

Viewer • Updated Dec 2, 2024 • 661 • 50

refusals/llama_3_1_405b_classifications_multi_human

Viewer • Updated Dec 2, 2024 • 661 • 51

refusals/llama_3_1_8b_classifications_multi_human

Viewer • Updated Dec 2, 2024 • 660 • 54

refusals/gpt_4o_mini_classifications_multi_human

Viewer • Updated Dec 2, 2024 • 661 • 47

refusals/gpt_4o_classifications_multi_human

Viewer • Updated Dec 2, 2024 • 661 • 46

refusals/predictions_logistic_classifier

Viewer • Updated Dec 2, 2024 • 607 • 59

refusals/human_classifications

Viewer • Updated Dec 2, 2024 • 8.65k • 48

refusals/RoboRefusal_Ultra_Final

Viewer • Updated Dec 1, 2024 • 7.2M • 60

refusals/RoboRefusal_Ultra2

Viewer • Updated Dec 1, 2024 • 7.1M • 58

refusals/RoboRefusal_Ultra

Viewer • Updated Nov 30, 2024 • 5.08M • 69

refusals/RoboRefusal_100K

Viewer • Updated Nov 30, 2024 • 104k • 38

mvh 

authored a paper 12 months ago

Black-Box Access is Insufficient for Rigorous AI Audits

Paper • 2401.14446 • Published Jan 25, 2024 • 3