concept activation vector

Controlling Large Language Models Through Concept Activation Vectors AAAI 2025 FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks ICML 2025 GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability ICCV 2025 Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence ICLR 2025 Demystifying Embedding Spaces using Large Language Models ICLR 2024 From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space AAAI 2024 LG-CAV: Train Any Concept Activation Vector with Language Guidance NeurIPS 2024 Uncovering Safety Risks of Large Language Models through Concept Activation Vector NeurIPS 2024 Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement NeurIPS 2023 Ripple: Concept-Based Interpretation for Raw Time Series Models in Education AAAI 2023 Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectors ACL 2022 Meaningfully debugging model mistakes using conceptual counterfactual explanations ICML 2022 Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors AAAI 2021 Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) ICML 2018