Re-examining low-rank adaptation for private LLM fine-tuning
cs.LG
Submitted: 2025-10-01
Updated: 2026-11-03
Terminology
Sources
- Differentially Private Bias-Term Fine-tuning of Foundation Models
- The Llama 3 Herd of Models
- Large Language Models Can Be Strong Differentially Private Learners
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- The E2E Dataset: New Challenges For End-to-End Generation
- Qwen3 Technical Report
- Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy
- DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- 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