AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers introduce RePAIR, a framework enabling users to instruct large language models to forget harmful knowledge, misinformation, and personal data through natural language prompts at inference time. The system uses a training-free method called STAMP that manipulates model activations to achieve selective unlearning with minimal computational overhead, outperforming existing approaches while preserving model utility.
AIBullisharXiv – CS AI · Mar 117/10
🧠Researchers have developed UltraEdit, a breakthrough method for efficiently updating large language models without retraining. The approach is 7x faster than previous methods while using 4x less memory, enabling continuous model updates with up to 2 million edits on consumer hardware.
AIBullisharXiv – CS AI · Mar 37/103
🧠Researchers have identified that the 'reversal curse' in language models - their inability to infer 'B is A' from 'A is B' - can be overcome through bilinear representation structures. Training models on synthetic relational knowledge graphs creates internal geometries that enable consistent model editing and logical inference of reverse facts.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers compare four neural network architectures for factual knowledge propagation in question-answering systems, finding that repeated shared memory access enables out-of-distribution generalization ('grokking'), but only architectures with fine-grained addressable memory can effectively propagate edited facts. The study dissociates learning capability from editing affordance, revealing that looped computation and explicit memory mechanisms serve different functional purposes.
AINeutralarXiv – CS AI · Jun 26/10
🧠RuleEdit is an interactive AI system that helps practitioners detect model failures and preview the impact of edits before implementation. Tested in stroke rehabilitation assessment, it increased human-AI performance by 14.16% through interpretable failure signals and prospective impact previews, though it revealed a critical local-global performance tradeoff where edits optimizing specific cases can degrade broader performance.
AINeutralarXiv – CS AI · May 296/10
🧠Researchers propose Orthogonal Concept Erasure (OCE), a new method for removing undesired content from diffusion models that uses multiplicative parameter updates instead of additive ones. OCE achieves faster, more precise concept erasure while preserving model generative quality, capable of erasing up to 100 concepts in 4.3 seconds.
AINeutralarXiv – CS AI · May 126/10
🧠Researchers present HoReN, a novel method for editing large language models that preserves original knowledge while incorporating new information through a codebook-based external memory system. The approach uses Hopfield networks and angular similarity retrieval to handle up to 50,000 sequential edits, significantly outperforming existing model editing techniques that degrade at scale.
AIBullisharXiv – CS AI · Mar 176/10
🧠Researchers introduce RAZOR, a new framework for efficiently removing sensitive information from AI models like CLIP and Stable Diffusion without requiring full retraining. The method selectively edits specific layers and attention heads in transformer models to achieve targeted 'unlearning' while preserving overall performance.
🧠 Stable Diffusion
AIBullisharXiv – CS AI · Mar 166/10
🧠Researchers propose MetaKE, a new framework for knowledge editing in Large Language Models that addresses the 'Semantic-Execution Disconnect' through bi-level optimization. The method treats edit targets as learnable parameters and uses a Structural Gradient Proxy to align edits with the model's feasible manifold, showing significant improvements over existing approaches.
AINeutralarXiv – CS AI · Mar 175/10
🧠Researchers introduce SAKE, the first benchmark for editing auditory attribute knowledge in large audio-language models without requiring full retraining. The study reveals significant limitations in current editing methods, particularly with auditory generalization and sequential editing, while finding that fine-tuning modality connectors offers better performance than editing LLM backbones directly.
