Interpretability

Towards Interpretable and Efficient Automatic Reference-Based Summarization Evaluation EMNLP 2023 Towards Interpretable Deep Reinforcement Learning with Human-Friendly Prototypes ICLR 2023 Towards Interpretable Mental Health Analysis with Large Language Models EMNLP 2023 Towards Interpretable Video Anomaly Detection WACV 2023 Towards Interpreting and Utilizing Symmetry Property in Adversarial Examples AAAI 2023 Towards Last-layer Retraining for Group Robustness with Fewer Annotations NeurIPS 2023 Towards Mitigating LLM Hallucination via Self Reflection EMNLP 2023 Towards More Robust Interpretation via Local Gradient Alignment AAAI 2023 Towards preserving word order importance through Forced Invalidation EACL 2023 Towards Realistic Evaluation of Industrial Continual Learning Scenarios with an Emphasis on Energy Consumption and Computational Footprint ICCV 2023 Towards Reference Speech Characterization for Health Applications Interspeech 2023 Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4 EMNLP 2023 Towards Reliable Neural Specifications ICML 2023 Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective NeurIPS 2023 Towards Robust Metrics for Concept Representation Evaluation AAAI 2023 Towards Self-Interpretable Graph-Level Anomaly Detection NeurIPS 2023 Towards Supporting an Early Diagnosis of Multiple Sclerosis using Vocal Features Interspeech 2023 Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision CVPR 2023 Towards Trustworthy Explanation: On Causal Rationalization ICML 2023 Towards Understanding Omission in Dialogue Summarization ACL 2023 Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation CVPR 2023 Tracr: Compiled Transformers as a Laboratory for Interpretability NeurIPS 2023 Trade-off Between Efficiency and Consistency for Removal-based Explanations NeurIPS 2023 Trainability, Expressivity and Interpretability in Gated Neural ODEs ICML 2023 Training language models to summarize narratives improves brain alignment ICLR 2023