Interpretability

Capturing Failures of Large Language Models via Human Cognitive Biases NeurIPS 2022 Capturing Topic Framing via Masked Language Modeling EMNLP 2022 CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure EMNLP 2022 Causal Explanations and XAI CLeaR 2022 Causal Identification under Markov equivalence: Calculus, Algorithm, and Completeness NeurIPS 2022 CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior NeurIPS 2022 Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation ICLR 2022 CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks AISTATS 2022 Chain-of-Thought Prompting Elicits Reasoning in Large Language Models NeurIPS 2022 Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models NAACL 2022 Challenges in Measuring Bias via Open-Ended Language Generation NAACL 2022 CheckHARD: Checking Hard Labels for Adversarial Text Detection, Prediction Correction, and Perturbed Word Suggestion EMNLP 2022 Chinese Synesthesia Detection: New Dataset and Models ACL 2022 Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers NeurIPS 2022 CLEAR: Generative Counterfactual Explanations on Graphs NeurIPS 2022 CLEVA-Compass: A Continual Learning Evaluation Assessment Compass to Promote Research Transparency and Comparability ICLR 2022 CLEVRER-Humans: Describing Physical and Causal Events the Human Way NeurIPS 2022 COAT: Measuring Object Compositionality in Emergent Representations ICML 2022 Cognitive Simplification Operations Improve Text Simplification CoNLL 2022 Combining Feature and Instance Attribution to Detect Artifacts ACL 2022 CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Task EMNLP 2022 Communication breakdown: On the low mutual intelligibility between human and neural captioning EMNLP 2022 Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality? EMNLP 2022 Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound ICLR 2022 Complex Video Action Reasoning via Learnable Markov Logic Network CVPR 2022