Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Stereotype Bias Evaluation on StereoSet Gender

99.59LMS Score

LLaMa3-8b

46.747660.466374.18587.9037May 2, 2022Jan 2, 2023Sep 5, 2023May 8, 2024Jan 8, 2025Sep 11, 2025May 15, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.05
99.5957.784.3
2026.05
98.7654.8189.26
2026.05
92.9851.4490.21
2026.05
92.5658.9376.03
2026.05
92.1553.8585.05
2026.05
86.3459.6669.66
2026.05
86.0155.6276.34
2023.07
85.659.0570.11
2023.07
85.4758.6970.63
2023.07
85.4260.1168.16
2023.07
85.1258.1571.24
2023.07
84.856.9273.07
2023.07
84.7560.5266.93
2026.05
84.6556.0274.46
2023.07
84.6352.9779.61
2023.07
84.4456.6173.28
2026.05
84.4259.6668.12
2023.07
84.1760.2866.86
2023.07
82.6958.0969.31
2023.07
81.9156.4771.3
2023.07
81.7657.3369.78
2022.05
75.666.550.6
2022.05
7463.653.8
2023.07
48.7846.4445.31