Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations.

Yanda Chen Ruiqi Zhong Narutatsu Ri Chen Zhao 0013 He He 0001 Jacob Steinhardt Zhou Yu Kathleen R. McKeown Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations. 2024 ICML https://proceedings.mlr.press/v235/chen24bl.html https://openreview.net/forum?id=99jx5U81jx conf/icml/2024 db/conf/icml/icml2024.html#ChenZRZ0SYM24 7880-7904