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

longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks. NAACL 2022
Linear tree shap NIPS 2022
KerGNNs: Interpretable Graph Neural Networks with Graph Kernels AAAI 2022
VisCUIT: Visual Auditor for Bias in CNN Image Classifier CVPR 2022
Probing via Prompting NAACL 2022
Pathologies of Pre-trained Language Models in Few-shot Fine-tuning ACL 2022
On the Sensitivity and Stability of Model Interpretations in NLP ACL 2022
Fair and Optimal Decision Trees: A Dynamic Programming Approach NIPS 2022
Double Trouble: How to not Explain a Text Classifier’s Decisions Using Counterfactuals Synthesized by Masked Language Models? IJCNLP 2022
Discourse on ASR Measurement: Introducing the ARPOCA Assessment Tool ACL 2022
Do Explanations Explain? Model Knows Best CVPR 2022
Accurate Shapley Values for explaining tree-based models AISTATS 2022
FR: Folded Rationalization with a Unified Encoder NIPS 2022
Neural Basis Models for Interpretability NIPS 2022
Explaining Preferences with Shapley Values NIPS 2022
Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts NAACL 2022
Locally Distributed Activation Vectors for Guided Feature Attribution COLING 2022
CounteRGAN: Generating counterfactuals for real-time recourse and interpretability using residual GANs UAI 2022
Mitigating the Inconsistency Between Word Saliency and Model Confidence with Pathological Contrastive Training ACL 2022
Can Rationalization Improve Robustness? NAACL 2022
Model Distillation for Faithful Explanations of Medical Code Predictions ACL 2022
Analyzing Encoded Concepts in Transformer Language Models NAACL 2022
CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior NIPS 2022
Combining Feature and Instance Attribution to Detect Artifacts ACL 2022
On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similarity NIPS 2022