ResearchDatasetsDeceptive Alignment Benchmark (DAB)FollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsLatent Knowledge ElicitationDeceptive Alignment Benchmark (DAB) 400 scenarios81.2Elicitation Accuracy12
Latent Knowledge ElicitationDeceptive Alignment Benchmark (DAB) 400 scenarios81.2Elicitation Accuracy12