Skip to main content
Search

# Concept Erasure

4 related articles

Subscribe to updates
  1. arXiv

    Erasing a group gap from a learning model does not close it: an audit prices the removal at about 0.021 Brier score on new Eedi classes

    Adaptive tutors often pursue fairness by erasing the group signal from a learned model, but what is erased is the mean group contrast in predictions, not the real gap. The work gives a closed-form minimum extra error for this removal and a three-stage audit that fits on training units, announces the cost on validation units and tests on independent units. On three real data sets the erased model predicts almost none of an observed gap; on Eedi, with a knowledge-tracing network selected on separate units, the audit accepted the announced cost in all five splits, the measured cost fell inside the announced interval in all five, and the gap reduction transferred to new classes in four.

  2. arXiv

    Brain MRI foundation models lose accuracy on a new dataset: not because they remember the source, but because each dataset encodes the sequence along different directions

    Across 17 public brain MRI datasets and eight frozen representations, the sequence is recognizable inside every dataset yet collapses on an unseen one, because each dataset encodes the sequence difference along different directions rather than because the features remember where a scan came from.

  3. arXiv

    RASteer erases concepts in diffusion models via retain-aware activation steering, matching or outperforming evaluated activation-steering and weight-editing baselines across backbones and benchmarks

    The work proposes Retain-aware Activation Steering (RASteer), a training-free method that first builds a retain subspace from the concepts to preserve, then uses Retain-Orthogonal Steering (ROS) to remove components aligned with this subspace from the erasure direction, and further introduces Overlap-Adaptive Calibration (OAC) to control, at each layer and denoising step, how much of each shared component is removed based on the overlap between the erasure direction and the retain subspace, thereby better balancing target erasure and concept preservation; experiments on unsafe-content, instance, and artistic-style erasure across multiple backbones and benchmarks show RASteer matches or outperforms the activation-steering and weight-editing baselines evaluated.

  4. arXiv

    FADE erases 16 concepts at once from a single text-to-video model, cutting residual object accuracy to 4.9% from the strongest baseline's 15.5% while staying within 0.9% of the unedited VBench average

    The work proposes FADE, a multi-concept unlearning framework for text-to-video diffusion transformers that first applies a joint closed-form key/value edit suppressing all target concepts, then trains per-concept frame-aware low-rank adapters gated by the frame index and denoising timestep to remove residual per-frame leakage, and combines adapters by a similarity-based soft router; erasing 16 concepts (objects, artistic styles, and nudity) from a single Wan2.1-T2V-1.3B backbone, FADE reduces residual object-benchmark accuracy to 4.9% against 15.5% for the strongest of eight baselines, keeps the VBench average within 0.9% of the unedited model, and the ranking holds under a VLM judge and a blinded human study.

You’re all caught up