2024 "feature attribution methods" Papers
2 papers found
Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
Xuexin Chen, Ruichu Cai, Zhengting Huang et al.
ICML 2024posterarXiv:2402.08845
GiLOT: Interpreting Generative Language Models via Optimal Transport
Xuhong Li, Jiamin Chen, Yekun Chai et al.
ICML 2024poster