Pith. sign in

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

arxiv 2402.13659 v2 pith:P4WS4P2G submitted 2024-02-21 cs.CR cs.CL

classification cs.CRcs.CL
keywords instructionssyntheticfine-tuningmodelsrealaligninghumanlanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation

    cs.CR 2025-11 conditional novelty 6.0 of 10

    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.

  2. GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation

    cs.CL 2025-08 conditional novelty 4.0 of 10

    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.

  3. Small Language Models: Architectures, Techniques, Evaluation, Problems and Future Adaptation

    cs.CL 2025-05 unverdicted novelty 2.0 of 10

    A survey of small language models that organizes known methods into taxonomies but adds no new models, data, or validated benchmarks.

Pith tools