Toxicity Detection

Benchmarks

Dataset Name	SOTA Method	Metric
ToxiGen	TaT (Disp.)	Score84.23	95	1mo ago
Toxicity Detection 64 model-persona combinations (8 models x 8 personas)	SVM Meta-Ensemble	Win Count58	56	4mo ago
Implicit Hate	DrICL	Accuracy63.1	52	1mo ago
ToxicChat	SafeGPT	F1 Score1	45	1mo ago
Adv	InfICL	Accuracy59.74	42	1mo ago
Hosseini’s 1st Negated Sentence 1.0 (test)	Bert+Bi-LSTM	Toxicity Score80.6	24	4mo ago
HateXplain		AUC90.44	21	4mo ago
CivilComments BERT (test)		Oracle ECE0.57	20	2mo ago
CivilComments-WILDS (test)		Average Accuracy92.7	19	4mo ago
Bangla		Accuracy91.66	15	3mo ago
CivilComments (test)	JTT	WGA78.8	14	3mo ago
Wikipedia Detox	GNN-based framework	Accuracy91.3	13	4mo ago
RealTox Challenging	Trajectory (Raw)	Accuracy98.92	12	4mo ago
RealTox Standard	Trajectory (Raw)	Accuracy87.56	12	4mo ago
CAD full	ContextRNN	F1 Score52.5	11	4mo ago
BAD		F1 Score80.8	11	4mo ago
BBF		F1 Score66.4	11	4mo ago
Toxicity Detection (TD) suite implicit adv toxigen	InfICL	Implicit Score60	10	1mo ago
L2DTnH (test)	IGC-BERT	Accuracy96.05	10	3mo ago
Perturbed Text	ContiGuard	Performance (Insert)85.57	10	4mo ago
Hate Speech	I-Vanilla	Accuracy75.73	10	4mo ago
Civil	I-Simul	Accuracy87.06	10	4mo ago
CAD context	ContextRNN	F1 Score68.1	10	4mo ago
HQG	ContextSum	F1 Score91.1	10	4mo ago
HQR	ContextSingle	F1 Score81.1	10	4mo ago

Showing 25 of 67 rows