·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
New York becomes the first state to enact a data center moratorium2h◆FAD-SA-GRU: Enhancing Hate Speech Detection in Algerian Dialect Through Feature-Augmented Self-Attention GRU Networks7h◆RL Forgets! Towards Continual Policy Optimization7h◆Learnable Mixed Nash Equilibria are Collectively Rational7h◆Oracle-Efficient Combinatorial Semi-Bandits7h◆SMETA-ZSL:Semantic Meta-Alignment for Zero-Shot Threat Classification7h◆Efficiently Adapting Spoken Language Models for the Singaporean Context7h◆Global Merger-Arbitrage Forecasting with Language Models7h◆Dzongkha Next Word Prediction System7h◆Production and Perception in LLMs: A Token Probability Approach7h◆Loci Similes: A Benchmark for Extracting Intertextualities in Latin Literature7h◆Manifold Constrained Tabular Deep Neural Networks7h◆Scaffold splits hide structural-frontier failures in ADMET models7h◆The Spectral Structure of Latent Treatment Effects7h◆Omni-Decision: A Progressive Evidence-State Agent System for Omni-Modal QA7h◆Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns7h◆Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction7h◆Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models7h◆Efficient Online Proportional Sampling with Applications to Smoothed Online Learning7h◆CDFM: Towards a General-Purpose Causal Discovery Foundation Model7h◆New York becomes the first state to enact a data center moratorium2h◆FAD-SA-GRU: Enhancing Hate Speech Detection in Algerian Dialect Through Feature-Augmented Self-Attention GRU Networks7h◆RL Forgets! Towards Continual Policy Optimization7h◆Learnable Mixed Nash Equilibria are Collectively Rational7h◆Oracle-Efficient Combinatorial Semi-Bandits7h◆SMETA-ZSL:Semantic Meta-Alignment for Zero-Shot Threat Classification7h◆Efficiently Adapting Spoken Language Models for the Singaporean Context7h◆Global Merger-Arbitrage Forecasting with Language Models7h◆Dzongkha Next Word Prediction System7h◆Production and Perception in LLMs: A Token Probability Approach7h◆Loci Similes: A Benchmark for Extracting Intertextualities in Latin Literature7h◆Manifold Constrained Tabular Deep Neural Networks7h◆Scaffold splits hide structural-frontier failures in ADMET models7h◆The Spectral Structure of Latent Treatment Effects7h◆Omni-Decision: A Progressive Evidence-State Agent System for Omni-Modal QA7h◆Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns7h◆Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction7h◆Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models7h◆Efficient Online Proportional Sampling with Applications to Smoothed Online Learning7h◆CDFM: Towards a General-Purpose Causal Discovery Foundation Model7h◆
News/Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem
arxiv
PublishedJuly 13, 2026 at 4:00 AM
—neutral

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2607.09236v1 Announce Type: new Abstract: Machine unlearning in LLMs is the targeted removal of specific knowledge while preserving all other capabilities, critical for privacy and safety. Yet existing benchmarks measure it unreliably. They miss knowledge that resurfaces under paraphrased or i

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivFAD-SA-GRU: Enhancing Hate Speech Detection in Algerian Dialect Through Feature-Augmented Self-Attention GRU Networks7harxivRL Forgets! Towards Continual Policy Optimization7harxivLearnable Mixed Nash Equilibria are Collectively Rational7harxivOracle-Efficient Combinatorial Semi-Bandits7h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews