← Core Methods
Machine Learning › Core Methods ›

Interpretability

349 directly classified papers

Papers per year

Papers

Defining and Quantifying the Emergence of Sparse Concepts in DNNs CVPR 2023
Trusted Fine-Grained Image Classification through Hierarchical Evidence Fusion AAAI 2023
Experimental Observations of the Topology of Convolutional Neural Network Activations AAAI 2023
Class based Influence Functions for Error Detection ACL 2023
Explaining Random Forests Using Bipolar Argumentation and Markov Networks AAAI 2023
Latent Autoregressive Source Separation AAAI 2023
CREST: A Joint Framework for Rationalization and Counterfactual Text Generation ACL 2023
The KITMUS Test: Evaluating Knowledge Integration from Multiple Sources ACL 2023
Neural Representations Reveal Distinct Modes of Class Fitting in Residual Convolutional Networks AAAI 2023
Interpreting Unfairness in Graph Neural Networks via Training Node Attribution AAAI 2023
Log-linear Guardedness and its Implications ACL 2023
Efficient Shapley Values Estimation by Amortization for Text Classification ACL 2023
Very Fast, Approximate Counterfactual Explanations for Decision Forests AAAI 2023
Contrastive Learning with Adversarial Examples for Alleviating Pathology of Language Model ACL 2023
Explaining How Transformers Use Context to Build Predictions ACL 2023
Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model Predictions ACL 2023
Unsupervised Selective Rationalization with Noise Injection ACL 2023
Symbolic Metamodels for Interpreting Black-Boxes Using Primitive Functions AAAI 2023
REV: Information-Theoretic Evaluation of Free-Text Rationales ACL 2023
On the Interpretability and Significance of Bias Metrics in Texts: a PMI-based Approach ACL 2023
Black-box language model explanation by context length probing ACL 2023
Local Path Integration for Attribution AAAI 2023
COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP ACL 2023
Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods ACL 2023
Rethinking Interpretation: Input-Agnostic Saliency Mapping of Deep Visual Classifiers AAAI 2023