Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA

arXiv:2506.20856 · cs.LG, cs.AI, cs.CL, cs.CR · Submitted 2025-06-25 · Read on arXiv

cs.LG, cs.AI, cs.CL, cs.CR

Submitted: 2025-06-25

Updated: 2025-06-25

Terminology

• Fine-Tuning — 8× in this paper · explained in 5 episodes
• Memorization — 7× in this paper · explained in 4 episodes
• LoRA Fine-Tuning — 2× in this paper · explained in 3 episodes
• Language Models (LLMs) — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 9 episodes

Related papers

• Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
• Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
• Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model
• D-STEER: Two-Way Control of DPO-Induced Safety Behavior in Activation Space
• Optimal hypersurface decision trees
• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation