Interpretability

VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers EMNLP 2023 Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution NeurIPS 2023 Visual Explanations via Iterated Integrated Attributions ICCV 2023 Visualizing Global Explanations of Point Cloud DNNs WACV 2023 Visual Programming for Step-by-Step Text-to-Image Generation and Evaluation NeurIPS 2023 ViT-CX: Causal Explanation of Vision Transformers IJCAI 2023 VLC-BERT: Visual Question Answering With Contextualized Commonsense Knowledge WACV 2023 VLSlice: Interactive Vision-and-Language Slice Discovery ICCV 2023 VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering ICCV 2023 WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes NeurIPS 2023 We’re Afraid Language Models Aren’t Modeling Ambiguity EMNLP 2023 What Can We Learn from Unlearnable Datasets? NeurIPS 2023 What Do Deep Saliency Models Learn about Visual Attention? NeurIPS 2023 What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric ACL 2023 What Does BERT actually Learn about Event Coreference? Probing Structural Information in a Fine-Tuned Dutch Language Model EACL 2023 What Do You MEME? Generating Explanations for Visual Semantic Role Labelling in Memes AAAI 2023 What is the Real Intention behind this Question? Dataset Collection and Intention Classification ACL 2023 What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain Adaptation ACL 2023 What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations EMNLP 2023 What social attitudes about gender does BERT encode? Leveraging insights from psycholinguistics ACL 2023 What the DAAM: Interpreting Stable Diffusion Using Cross Attention ACL 2023 When and Why Does Bias Mitigation Work? EMNLP 2023 When are Lemons Purple? The Concept Association Bias of Vision-Language Models EMNLP 2023 When are post-hoc conceptual explanations identifiable? UAI 2023 When does Privileged information Explain Away Label Noise? ICML 2023