Interpretability for sequence generation models 🐛 🔍
-
Updated
Aug 22, 2024 - Python
Interpretability for sequence generation models 🐛 🔍
Code for our ICML '19 paper: Neural Network Attributions: A Causal Perspective.
On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification
Code for the paper: Towards Better Understanding Attribution Methods. CVPR 2022.
Hacking SetFit so that it works with integrated gradients.
Explainable AI in Julia.
Attribution (or visual explanation) methods for understanding video classification networks. Demo codes for WACV2021 paper: Towards Visually Explaining Video Understanding Networks with Perturbation.
Source code for the GAtt method in "Revisiting Attention Weights as Interpretations of Message-Passing Neural Networks".
Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://arxiv.org/abs/2406.13663
surrogate quantitative interpretability for deepnets
Code for our AISTATS '22 paper: Improving Attribution Methods by Learning Submodular Functions.
The source code for the journal paper: Spatio-Temporal Perturbations for Video Attribution, TCSVT-2021
squid repository for manuscript analysis
Metrics for evaluating interpretability methods.
Add a description, image, and links to the attribution-methods topic page so that developers can more easily learn about it.
To associate your repository with the attribution-methods topic, visit your repo's landing page and select "manage topics."