Our new X account is live! Follow @wizwand_team for updates

Toxicity Evaluation on RealToxicityPrompts

0Toxicity Score

Adversarial loss

Updated 4d ago

Evaluation Results

Method	Links
Adversarial loss 2024.05		0	-	-	-	-	-	-
Adversarial loss 2024.05		0	-	-	-	-	-	-
RepNoise 2024.05		0	-	-	-	-	-	-
Gradient Ascent 2024.05		0.05	-	-	-	-	-	-
RepNoise 2024.05		0.05	-	-	-	-	-	-
RepNoise 2024.05		0.07	-	-	-	-	-	-
Phi-2 + BiasDPO 2024.07		0.11	-	-	-	-	-	-
Gradient Ascent 2024.05		0.12	-	-	-	-	-	-
Mistral-7B 2024.07		0.14	-	-	-	-	-	-
Security Vectors 2024.05		0.16	-	-	-	-	-	-
Phi-2 2024.07		0.17	-	-	-	-	-	-
Security Vectors 2024.05		0.17	-	-	-	-	-	-
RepNoise 2024.05		0.17	-	-	-	-	-	-
Gemma-2B 2024.07		0.19	-	-	-	-	-	-
StableLM-3B 2024.07		0.19	-	-	-	-	-	-
Vaccine 2024.05		0.19	-	-	-	-	-	-
Base 2024.05		0.24	-	-	-	-	-	-
Security Vectors 2024.05		0.35	-	-	-	-	-	-
Security Vectors 2024.05		0.36	-	-	-	-	-	-
Base 2024.05		0.4	-	-	-	-	-	-
Gradient Ascent 2024.05		0.44	-	-	-	-	-	-
Vaccine 2024.05		0.46	-	-	-	-	-	-
Vaccine 2024.05		0.7	-	-	-	-	-	-
Base 2024.05		0.71	-	-	-	-	-	-
Vaccine 2024.05		0.72	-	-	-	-	-	-
Base 2024.05		0.74	-	-	-	-	-	-
Gradient Ascent 2024.05		0.76	-	-	-	-	-	-
Adversarial loss 2024.05		0.77	-	-	-	-	-	-
Adversarial loss 2024.05		0.78	-	-	-	-	-	-
DAPT (nontoxic) 2022.02		-	0.44	0.65	0.38	37	72	28
DAPT (nontoxic) 2022.02		-	0.47	0.69	0.41	43	78	33
DAPT (nontoxic) 2022.02		-	0.47	0.69	0.41	43	79	33
DAPT (nontoxic) 2022.02		-	0.48	0.69	0.42	45	79	35
DAPT (nontoxic) 2022.02		-	0.5	0.71	0.45	49	82	39
SGEAT (augmented) 2022.02		-	0.39	0.63	0.33	30	69	19
SGEAT (augmented) 2022.02		-	0.42	0.68	0.35	36	77	24
SGEAT (augmented) 2022.02		-	0.43	0.68	0.37	37	77	26
SGEAT (augmented) 2022.02		-	0.44	0.68	0.37	38	76	28
SGEAT (augmented) 2022.02		-	0.46	0.7	0.4	43	80	32
SGEAT (augmented) 2022.02		-	0.45	0.69	0.39	41	78	31
SGEAT (augmented) 2022.02		-	0.44	0.67	0.38	39	76	29