SOTA Deception Detection benchmarks and papers with code

Benchmarks

Dataset Name	SOTA Method	Metric
Varied Deception		Apollo Score0.95	32	1mo ago
DOLOs	DecepGPT	Accuracy73.23	28	1mo ago
XCHECK 1.0 (test)	NVILA	F1 Score87.44	28	4mo ago
MU3D	DecepGPT	Accuracy61.25	26	1mo ago
Bag-of-Lies (BoL)	DecepGPT	Accuracy63.46	24	1mo ago
InstrumentalEval (InstEval)	STATEWITNESS	AUROC0.867	16	1mo ago
Agentic Misalignment	STATEWITNESS	AUROC92.4	16	1mo ago
Insider Trading	Self-Evaluation	AUROC100	16	1mo ago
MASK	STATEWITNESS	AUROC0.822	16	1mo ago
Sandbagging (Sandbag)	STATEWITNESS	AUROC99.9	16	1mo ago
Roleplaying	Self-Evaluation	AUROC99.8	16	1mo ago
Instructed Deception		AUROC99.6	16	1mo ago
DeceptionBench (full 600-sample)	DECOR	Response AUROC97.4	15	2mo ago
R, M, B1, B2, D, and E Cross-domain generalization	MM-IDGM	Performance: (R & M) -> B157.85	12	1mo ago
MuDD Audio modality (test)	GPD	F1 Score20.1	11	3mo ago
MuDD Video modality (test)	GPD	F1 Score16.7	11	3mo ago
SEUMLD	GenLie	F1 Score42.39	10	4mo ago
Real-Life Trial		F1 Score93.55	10	4mo ago
MDPE	GenLie	F1 Score38.97	10	4mo ago
DOLOS, MDPE, RLTD, Box of Lies Summary	ThinkDeception	Average Accuracy73.76	9	1mo ago
Box of Lies Cross-domain	ThinkDeception	Accuracy69.41	9	1mo ago
RLTD Cross-domain	ThinkDeception	Accuracy71.2	9	1mo ago
MDPE In-domain	ThinkDeception	Accuracy77.6	9	1mo ago
DOLOS In-domain	ThinkDeception	Accuracy76.83	9	1mo ago
MDPE and DDEP	CLB-HBB-Bai-Rel-DDEP	Accuracy66.63	9	3mo ago

Showing 25 of 48 rows