Sensitivity Inflation from Cross-Record Precision Routing in Private Quantized Fine-Tuning
cs.LG
Submitted: 2026-11-01
Updated: 2026-11-01
Code: https://github.com/huggingface/transformers
Terminology
Sources
- QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models
- LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
- QLoRA: Efficient Finetuning of Quantized LLMs
- TinyStories: How Small Can Language Models Be and Still Speak Coherent English?
- Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
- DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling
- KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
- Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation
- FP8 Formats for Deep Learning
- Debugging Differential Privacy: A Case Study for Privacy Auditing
- Opacus: User-Friendly Differential Privacy Library in PyTorch
- OPT: Open Pre-trained Transformer Language Models
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