Interpretability

KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations ACL 2023 K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs ICML 2023 K-UniMorph: Korean Universal Morphology and its Feature Schema ACL 2023 Label-free Concept Bottleneck Models ICLR 2023 Labeling Neural Representations with Inverse Recognition NeurIPS 2023 Language-Agnostic Bias Detection in Language Models with Bias Probing EMNLP 2023 Language model acceptability judgements are not always robust to context ACL 2023 Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting NeurIPS 2023 Language Models with Rationality EMNLP 2023 Large language models transition from integrating across position-yoked, exponential windows to structure-yoked, power-law windows NeurIPS 2023 Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning EMNLP 2023 LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions ICCV 2023 LEACE: Perfect linear concept erasure in closed form NeurIPS 2023 Learning Analytical Posterior Probability for Human Mesh Recovery CVPR 2023 Learning Bottleneck Concepts in Image Classification CVPR 2023 Learning Concise and Descriptive Attributes for Visual Recognition ICCV 2023 Learning How to MIMIC: Using Model Explanations To Guide Deep Learning Training WACV 2023 Learning Interpretable Style Embeddings via Prompting LLMs EMNLP 2023 Learning Interpretable Temporal Properties from Positive Examples Only AAAI 2023 Learning Neuro-Symbolic World Models with Conversational Proprioception ACL 2023 Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection CVPR 2023 Learning Perturbations to Explain Time Series Predictions ICML 2023 Learning Prescriptive ReLU Networks ICML 2023 Learning Symbolic Models for Graph-structured Physical Mechanism ICLR 2023 Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning ACL 2023