Interpretability

Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models EMNLP 2024 Towards Learning and Explaining Indirect Causal Effects in Neural Networks AAAI 2024 Towards Modeling Uncertainties of Self-Explaining Neural Networks via Conformal Prediction AAAI 2024 Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQA AAAI 2024 Towards Multi-dimensional Explanation Alignment for Medical Classification NeurIPS 2024 Towards Neuron Attributions in Multi-Modal Large Language Models NeurIPS 2024 Towards Reducing Diagnostic Errors with Interpretable Risk Prediction NAACL 2024 Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks ICLR 2024 Towards Robust Saliency Maps ACML 2024 Towards Robust Visual Understanding: from Recognition to Reasoning AAAI 2024 Towards Scalable and Versatile Weight Space Learning ICML 2024 Towards Self-Attention Understanding for Automatic Articulatory Processes Analysis in Cleft Lip and Palate Speech Interspeech 2024 Towards Supporting Legal Argumentation with NLP: Is More Data Really All You Need? EMNLP 2024 Towards the Dynamics of a DNN Learning Symbolic Interactions NeurIPS 2024 Towards Transparent Time Series Forecasting ICLR 2024 Towards Trustworthy Autonomous Systems via Conversations and Explanations AAAI 2024 Towards Trustworthy Deep Learning AAAI 2024 Towards Understanding Attention-based Reasoning through Graph Structures in Medical Codes Classification ACL 2024 Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing CVPR 2024 Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis EMNLP 2024 Towards Verifiable Text Generation with Evolving Memory and Self-Reflection EMNLP 2024 TOWER: Tree Organized Weighting for Evaluating Complex Instructions EMNLP 2024 ToXCL: A Unified Framework for Toxic Speech Detection and Explanation NAACL 2024 TpT-ADE: Transformer Based Two-Phase ADE Extraction CoNLL 2024 Tracking linguistic information in transformer-based sentence embeddings through targeted sparsification ACL 2024