Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

BiasQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Chain-of-Thought Faithfulness EvaluationBiasQA
Unfaithful Explanation Rate2.4
14
Explanation Faithfulness EvaluationBiasQA (test)
Greedy20.7
7
Showing 2 of 2 rows