删概念像切肿瘤：只切坏的不碰好的
AI模型内部存储着各种概念（性别、年龄、物体等），但概念之间常常纠缠在一起。比如你想让模型“忘记”性别，它可能连带着把“长发”也忘了，因为两者在数据中常一起出现。这篇论文提出一个反直觉的思路：模型内部表示其实集中在某个低维“流形”上（就像数据蜷缩在一个弯曲的曲面上），那么只要把删除操作限制在这个流形内，就能精准移除目标概念而不伤及其他。他们据此开发了MANCE方法，在119个测试场景（包括文本和图像）中，相比现有方法，在保持其他信息不变的前提下，将目标概念的泄露降低了30%以上。这不是你明天能直接用的工具，但它揭示了AI可解释性和公平性干预的一个新方向：尊重数据的内在结构，而不是蛮力抹除。
📄 原文摘要(英文)
Concept erasure aims to remove a target concept from a representation while preserving the other information encoded in it. This is difficult because representations encode many concepts that are often correlated with the erasure target, so removing the target risks damaging them. We propose the Manifold Constraint Hypothesis (MCH): if natural representations concentrate on a structured, lower-dimensional manifold, then interventions should be constrained to that manifold and better preserve other information encoded in the representation during interventions. We instantiate MCH in a new concept erasure method: MANifold aware Concept Erasure (MANCE). MANCE performs iterative updates to the representations using signals from a classifier that predicts a target concept. We estimate the manifold using representations obtained from natural inputs, and then we project the concept removal update to the estimated manifold. We perform extensive evaluation on 119 settings spanning text and vision, including 13 language models, three NLP concepts, and 40 CelebA-CLIP attributes. Employing MANCE on top of previous methods shows consistent improved leakage results. We also introduce MANCE+ and MANCE++, which prepend a closed-form erasure algorithm before employing MANCE, achieving better leakage--surgicality tradeoffs relative to matched full-space updates. MANCE++, our best method, achieves state-of-the-art results on nonlinear concept erasure. These results support MCH in the erasure setting: interventions should be constrained to the natural representation manifold.