arXiv AI
Harmful Partial Interventions and Benign Leakage in Concept-based Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Aug 21
ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language Models
arXiv:2608. 20338v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly require selective removal of harmful or sensitive knowledge, called unlearning, yet existing methods and benchmarks fail to evaluate this capability completely.
arXiv AI
Jun 10
In Defense of Information Leakage in Concept-based Models
arXiv:2606. 10669v1 Announce Type: cross Abstract: Concept-based models (CMs), deep neural networks that ground their predictions on representations aligned with human-understandable concepts (e.
arXiv Machine Learning
Jul 24
Concept Concentration for Faithful Representation Intervention
arXiv:2505. 18672v2 Announce Type: replace Abstract: Representation intervention aims to localize and modify the representations that encode the underlying concepts in large language models (LLMs) to elicit the aligned and expected behaviors.
arXiv AI
Oct 9
Towards Reasonable Concept Bottleneck Models
The paper introduces CREAMs, a flexible framework for Concept Bottleneck Models that allows explicit encoding of concept‑concept and concept‑task relationships such as mutual exclusivity, hierarchy, and correlations. CREAMs can optionally use a regularized side‑channel to compensate for incomplete concept sets, maintaining competitive performance while encouraging concept‑grounded predictions. The authors also propose a new metric to assess interpretability when predictions partially rely on the side‑channel, and demonstrate that CREAMs support efficient interventions, avoid concept leakage, and match black‑box performance even with missing concepts.
arXiv AI
Jun 11
Models That Know How Evaluations Are Designed Score Safer
arXiv:2605. 28591v2 Announce Type: replace-cross Abstract: The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings.
arXiv Computer Vision
Sep 14
GRACE: Adaptive Concept Erasure with Geometry-Guided Retention in Diffusion Models
GRACE is a new framework for concept erasure in text-to-image diffusion models that uses a semantically weighted sensitive subspace to guide localized interventions and lightweight subspace-constrained adapters to avoid global semantic disruption. It replaces manual counterfactual prompts with an automatically decoupled safe-anchor mechanism and controls intervention strength through an energy-driven dynamic gating system. Experiments show GRACE improves NSFW reduction by 17.86% over five state-of-the-art methods while also reducing target CLIP Score and FID, indicating stronger concept suppression with better preservation of generative quality.