Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
cs.LG, cs.AI
Submitted: 2026-02-22
Updated: 2026-11-04
Terminology
Sources
- What Matters in Transformers? Not All Attention is Needed
- Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
- Gemma 3 Technical Report
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Revisit, Extend, and Enhance Hessian-Free Influence Functions
- A Comprehensive Study of Knowledge Editing for Large Language Models
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning