REVIEW 3 cited by
Privacy-Preserving Instructions for Aligning Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Service providers of large language model (LLM) applications collect user instructions in the wild and use them in further aligning LLMs with users' intentions. These instructions, which potentially contain sensitive information, are annotated by human workers in the process. This poses a new privacy risk not addressed by the typical private optimization. To this end, we propose using synthetic instructions to replace real instructions in data annotation and model fine-tuning. Formal differential privacy is guaranteed by generating those synthetic instructions using privately fine-tuned generators. Crucial in achieving the desired utility is our novel filtering algorithm that matches the distribution of the synthetic instructions to that of the real ones. In both supervised fine-tuning and reinforcement learning from human feedback, our extensive experiments demonstrate the high utility of the final set of synthetic instructions by showing comparable results to real instructions. In supervised fine-tuning, models trained with private synthetic instructions outperform leading open-source models such as Vicuna.
Forward citations
Cited by 3 Pith papers
-
CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation
An MPC-ML compiler that modularizes and auto-tunes operator approximations, delivering 1.2–1.8x speedups over an optimized baseline under user-set accuracy bounds.
-
GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation
GUARD is an LLM decoding method combining smoothed global entropy with local entropy spikes to self-tune contrastive search, plus a token-count penalty for speed.
-
Small Language Models: Architectures, Techniques, Evaluation, Problems and Future Adaptation
A survey of small language models that organizes known methods into taxonomies but adds no new models, data, or validated benchmarks.
Discussion (0). Continue with ORCID to comment.