conftrace_
← Core AI
Artificial Intelligence › Core AI ›

Interpretability

7,318 papers

Papers per year

Papers

Modeling Semantics and Pragmatics of Spatial Prepositions via Hierarchical Common-Sense Primitives ACL 2021
Plan Explanations that Exploit a Cognitive Spatial Model ACL 2021
Can Transformer Language Models Predict Psychometric Properties? ACL 2021
NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning ACL 2021
Realistic Evaluation Principles for Cross-document Coreference Resolution ACL 2021
Dependency Patterns of Complex Sentences and Semantic Disambiguation for Abstract Meaning Representation Parsing ACL 2021
Human-Model Divergence in the Handling of Vagueness ACL 2021
Evaluation Scheme of Focal Translation for Japanese Partially Amended Statutes ACL 2021
Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation ACL 2021
Context Sensitivity Estimation in Toxicity Detection ACL 2021
Targets and Aspects in Social Media Hate Speech ACL 2021
Generating Deep Networks Explanations with Robust Attribution Alignment ACML 2021
Shapley Flow: A Graph-based Approach to Interpreting Model Predictions AISTATS 2021
Efficient Computation and Analysis of Distributional Shapley Values AISTATS 2021
Interpretable Random Forests via Rule Extraction AISTATS 2021
Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations. AISTATS 2021
Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties AISTATS 2021
Influence Decompositions For Neural Network Attribution AISTATS 2021
Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks AISTATS 2021
Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression AISTATS 2021
An Analysis of LIME for Text Data AISTATS 2021
Towards a Theoretical Understanding of the Robustness of Variational Autoencoders AISTATS 2021
Moment Multicalibration for Uncertainty Estimation COLT 2021
The Sparse Vector Technique, Revisited COLT 2021
“It’s our fault!”: Insights Into Users’ Understanding and Interaction With an Explanatory Collaborative Dialog System CONLL 2021