Generalizable Model Editing Could Be More Than Direct Generalization

arXiv:2610.15707 · cs.LG, cs.CL · Submitted 2026-10-11 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-10-11

Updated: 2026-10-11

Terminology

• Generalization — 1× in this paper · explained in 13 episodes

Sources

• Qwen Technical Report
• The Llama 3 Herd of Models
• Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
• Emergent Abilities of Large Language Models
• Stable Knowledge Editing in Large Language Models
• Uncovering Entity Identity Confusion in Multimodal Knowledge Editing
• Qwen3 Technical Report
• A Comprehensive Study of Knowledge Editing for Large Language Models
• Modifying Memories in Transformer Models

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks