← Core Methods
Machine Learning › Core Methods ›

Interpretability

349 directly classified papers

Papers per year

Papers

Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations CVPR 2023
Defining and Quantifying the Emergence of Sparse Concepts in DNNs CVPR 2023
AttCAT: Explaining Transformers via Attentive Class Activation Tokens NIPS 2022
Are representations built from the ground up? An empirical examination of local composition in language models EMNLP 2022
Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes CVPR 2022
Explainable Metaphor Identification Inspired by Conceptual Metaphor Theory AAAI 2022
Fast and More Powerful Selective Inference for Sparse High-Order Interaction Model AAAI 2022
Analyzing the Use of Influence Functions for Instance-Specific Data Filtering in Neural Machine Translation EMNLP 2022
Tracing and Manipulating intermediate values in Neural Math Problem Solvers EMNLP 2022
Probing for targeted syntactic knowledge through grammatical error detection EMNLP 2022
Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification EMNLP 2022
Influence Functions for Sequence Tagging Models EMNLP 2022
Acceptability Judgements via Examining the Topology of Attention Maps EMNLP 2022
Do Feature Attribution Methods Correctly Attribute Features? AAAI 2022
ProtGNN: Towards Self-Explaining Graph Neural Networks AAAI 2022
Rethinking Influence Functions of Neural Networks in the Over-Parameterized Regime AAAI 2022
Constraint-Driven Explanations for Black-Box ML Models AAAI 2022
Entropy-Based Logic Explanations of Neural Networks AAAI 2022
Sufficient Reasons for Classifier Decisions in the Presence of Domain Constraints AAAI 2022
FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles AAAI 2022
Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations AAAI 2022
How to Find a Good Explanation for Clustering? AAAI 2022
Optimizing Binary Decision Diagrams with MaxSAT for Classification AAAI 2022
An Unsupervised Way to Understand Artifact Generating Internal Units in Generative Neural Networks AAAI 2022
Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers AAAI 2022