Toxicity Detection

Benchmarks

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

Showing 25 of 66 rows