Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations.
Yanda Chen, Ruiqi Zhong, Narutatsu Ri, Chen Zhao, He He, Jacob Steinhardt, Zhou Yu, Kathleen R. McKeown
Browse the full ICML paper archive.
Yanda Chen, Ruiqi Zhong, Narutatsu Ri, Chen Zhao, He He, Jacob Steinhardt, Zhou Yu, Kathleen R. McKeown
Browse the full ICML paper archive.