conftrace_

distributional distance

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

white-box method (1) embedding distance (1) back propagation (1) neuron masking (1) large language model (1) centered kernel alignment (1) embedding analysis (1) taylor expansion (1) gradient information (1) concept erasure (1)

Papers

Minimalist Concept Erasure in Generative Models ICML 2025 Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection EMNLP 2024 Revisiting the Evaluation of Image Synthesis with GANs NeurIPS 2023