Paper
LLMs & Texto
MANCE: Manifold Aware Concept Erasure
Manifold constraint hypothesis enables improved concept erasure by projecting updates onto estimated representation manifolds, achieving state-of-the-art results in nonlinear conce…
Hugging Face · Daily Papers
·Matan Avitan, Yoav Goldberg
·
·▲ 1 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Matan Avitan, Yoav Goldberg, Yanai Elazar
- 1 upvotes da comunidade
- Temas: concept erasure, manifold constraint hypothesis, representation manifold, iterative updates, classifier prediction, projection
Resumo
Resumo original (em inglês), extraído do paper:
Manifold constraint hypothesis enables improved concept erasure by projecting updates onto estimated representation manifolds, achieving state-of-the-art results in nonlinear concept removal.