Interpretability

Safe-Embed: Unveiling the Safety-Critical Knowledge of Sentence Encoders ACL 2024 SaGE: Evaluating Moral Consistency in Large Language Models COLING 2024 Saliency-driven Experience Replay for Continual Learning NeurIPS 2024 Saliency strikes back: How filtering out high frequencies improves white-box explanations ICML 2024 SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales EMNLP 2024 Scaling up Discovery of Latent Concepts in Deep NLP Models EACL 2024 SEAVER: Attention Reallocation for Mitigating Distractions in Language Models for Conditional Semantic Textual Similarity Measurement EMNLP 2024 Seeing Through VisualBERT: A Causal Adventure on Memetic Landscapes EMNLP 2024 Selective Explanations NeurIPS 2024 Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations EMNLP 2024 Self-Assessment Tests are Unreliable Measures of LLM Personality EMNLP 2024 Self-attention Networks Localize When QK-eigenspectrum Concentrates ICML 2024 Self-Calibrating Vicinal Risk Minimisation for Model Calibration CVPR 2024 SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning ICLR 2024 Self-contradictory reasoning evaluation and detection EMNLP 2024 Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives ACL 2024 Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation CVPR 2024 Self-Evaluation of Large Language Model based on Glass-box Features EMNLP 2024 SELF-EXPERTISE: Knowledge-based Instruction Dataset Augmentation for a Legal Expert Language Model NAACL 2024 SelfIE: Self-Interpretation of Large Language Model Embeddings ICML 2024 Self-Interpretable Graph Learning with Sufficient and Necessary Explanations AAAI 2024 Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection ICLR 2024 Self-Supervised Interpretable End-to-End Learning via Latent Functional Modularity ICML 2024 Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP EMNLP 2024 SEMANTIFY: Unveiling Memes with Robust Interpretability beyond Input Attribution IJCAI 2024