conftrace_

model interpretability

519 papers

Explore in graph

Co-occurring keywords

feature attribution (280) text classification (6793) neural network (6616) large language model (13587) explainable ai (480) model explanation (155) language model (4599) attention mechanism (4001) shapley value (206) representation learning (6206)

Papers

Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks NIPS 2021
Do Input Gradients Highlight Discriminative Features? NIPS 2021
Explaining Latent Representations with a Corpus of Examples NIPS 2021
WMDecompose: A Framework for Leveraging the Interpretable Properties of Word Mover’s Distance in Sociocultural Analysis EMNLP 2021
IrEne: Interpretable Energy Prediction for Transformers ACL 2021
Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation CVPR 2021
Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example AAAI 2021
Interpreting Multivariate Shapley Interactions in DNNs AAAI 2021
Counterfactual VQA: A Cause-Effect Look at Language Bias CVPR 2021
Improving Deep Learning Interpretability by Saliency Guided Training NIPS 2021
On Locality of Local Explanation Models NIPS 2021
Learning to Predict Trustworthiness with Steep Slope Loss NIPS 2021
Telling BERT’s Full Story: from Local Attention to Global Aggregation EACL 2021
Is Sparse Attention more Interpretable? IJCNLP 2021
Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability NIPS 2020
Inserting Information Bottlenecks for Attribution in Transformers EMNLP 2020
Understanding Neural Abstractive Summarization Models via Uncertainty EMNLP 2020
Transparency Promotion with Model-Agnostic Linear Competitors ICML 2020
XplaiNLI: Explainable Natural Language Inference through Visual Analytics COLING 2020
The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models EMNLP 2020
Efficient Estimation of Influence of a Training Instance EMNLP 2020
Pareto Probing: Trading Off Accuracy for Complexity EMNLP 2020
Interpretation of NLP models through input marginalization EMNLP 2020
A Diagnostic Study of Explainability Techniques for Text Classification EMNLP 2020
The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? EMNLP 2020