conftrace_

post-hoc explanation

48 papers

Explore in graph

Co-occurring keywords

model interpretability (519) feature attribution (280) explainable ai (480) model explanation (155) neural network (6616) large language model (13587) graph neural network (3962) convolutional neural network (4226) saliency map (125) text classification (6793)

Papers

Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat ICML 2023
ES-Mask: Evolutionary Strip Mask for Explaining Time Series Prediction (Student Abstract) AAAI 2023
Towards Better Understanding Attribution Methods CVPR 2022
Constraint-Driven Explanations for Black-Box ML Models AAAI 2022
Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification EMNLP 2022
An Empirical Study on Explanations in Out-of-Domain Settings ACL 2022
Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF NIPS 2022
Implications of Model Indeterminacy for Explanations of Automated Decisions NIPS 2022
Characterizing the risk of fairwashing NIPS 2021
Explanation-based Data Augmentation for Image Classification NIPS 2021
Towards Benchmarking the Utility of Explanations for Model Debugging NAACL 2021
Alignment Rationale for Natural Language Inference IJCNLP 2021
Argumentative XAI: A Survey IJCAI 2021
Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example AAAI 2021
Reliable Post hoc Explanations: Modeling Uncertainty in Explainability NIPS 2021
Generative causal explanations of black-box classifiers NIPS 2020
Contextualizing Hate Speech Classifiers with Post-hoc Explanation ACL 2020
Model Interpretability through the lens of Computational Complexity NIPS 2020
Regularizing Black-box Models for Improved Interpretability NIPS 2020
Sanity Checks for Saliency Metrics AAAI 2020
FLEX: Faithful Linguistic Explanations for Neural Net Based Model Decisions AAAI 2019
Many Faces of Feature Importance: Comparing Built-in and Post-hoc Feature Importance in Text Classification IJCNLP 2019
Evaluating neural network explanation methods using hybrid documents and morphosyntactic agreement ACL 2018