conftrace_

post-hoc interpretation

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

feature importance ranking (1) transformer hyperparameter (1) attribute function (1) neural network (1) explainable boosting machine (1) attribution method (1) feature visualization (1) interpretable model (1) confidence interval (1) hyperparameter tuning (1)

Papers

Confident Feature Ranking AISTATS 2024 Post-Hoc Interpretation of Transformer Hyperparameters with Explainable Boosting Machines EMNLP 2022 A Framework to Learn with Interpretation NeurIPS 2021 Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations EMNLP 2021