Pith. sign in

REVIEW 6 cited by

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2309.11765 v2 pith:H5QF55QR submitted 2023-09-21 cs.LG cs.CR

Xinyu Tang , Richard Shin , Huseyin A. Inan , Andre Manoel , Fatemehsadat Mireshghallah , Zinan Lin , Sivakanth Gopi , Janardhan Kulkarni
show 1 more author
Robert Sim
This is my paper · ORCID
classification cs.LGcs.CR
keywords privacyprivatealgorithmachievefew-shotin-contextlearningllms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We study the problem of in-context learning (ICL) with large language models (LLMs) on private datasets. This scenario poses privacy risks, as LLMs may leak or regurgitate the private examples demonstrated in the prompt. We propose a novel algorithm that generates synthetic few-shot demonstrations from the private dataset with formal differential privacy (DP) guarantees, and show empirically that it can achieve effective ICL. We conduct extensive experiments on standard benchmarks and compare our algorithm with non-private ICL and zero-shot solutions. Our results demonstrate that our algorithm can achieve competitive performance with strong privacy levels. These results open up new possibilities for ICL with privacy protection for a broad range of applications.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Not All Entities are Created Equal: A Dynamic Anonymization Framework for Privacy-Preserving RAG

    cs.CR 2026-03 unverdicted novelty 7.0 of 10

    TRIP-RAG dynamically anonymizes only high-risk entities in RAG knowledge bases via three context-aware metrics, achieving privacy comparable to full anonymization with under 35% recall drop and up to 56% better genera...

  2. Differentially Private Synthetic Data Release for Topics API Outputs

    cs.CR 2025-06 conditional novelty 6.0 of 10

    The paper presents a differentially private methodology and a public synthetic dataset of Topics API traces that match real re-identification risk within one standard deviation on two attacks.

  3. Differentially Private In-context Learning via Sampling Few-shot Mixed with Zero-shot Outputs

    cs.LG 2025-01 reject novelty 5.0 of 10

    DPS-MOZO samples each generated token from the product of per-example distributions mixed with the zero-shot distribution to make in-context learning differentially private without additive noise.

  4. Public Data Assisted Differentially Private In-Context Learning

    cs.AI 2025-09 conditional novelty 4.0 of 10

    A private ICL algorithm that aggregates LLM responses with DPM clustering and uses public data representatives achieves near-non-private utility at epsilon=1.

  5. Diverse And Private Synthetic Datasets Generation for RAG evaluation: A multi-agent framework

    cs.CL 2025-08 conditional novelty 4.0 of 10

    A multi-agent LLM framework generates synthetic QA datasets for RAG evaluation by combining clustering-based sampling, PII pseudonymization, and QA curation, with reported diversity gains and 0.75-0.90 masking accuracy.

  6. SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation

    cs.CR 2025-06 conditional novelty 3.0 of 10

    A systematization-of-knowledge survey that categorizes LLM privacy risks into training data, prompts, outputs, and agents, and reviews limitations of current mitigations.

Pith tools