Pith. sign in

REVIEW 5 cited by

Differentially Private Decoding in Large Language Models

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 2205.13621 v2 pith:JH5TUUQQ submitted 2022-05-26 cs.CL cs.LG

Jimit Majmudar , Christophe Dupuy , Charith Peris , Sami Smaili , Rahul Gupta , Richard Zemel This is my paper · ORCID
classification cs.CLcs.LG
keywords languagellmsmechanismmodelprivatedecodingdifferentiallylarge
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-trained model is adapted to a wide array of tasks via fine-tuning on task-specific datasets. LLMs, while effective, have been shown to memorize instances of training data thereby potentially revealing private information processed during pre-training. The potential leakage might further propagate to the downstream tasks for which LLMs are fine-tuned. On the other hand, privacy-preserving algorithms usually involve retraining from scratch, which is prohibitively expensive for LLMs. In this work, we propose a simple, easy to interpret, and computationally lightweight perturbation mechanism to be applied to an already trained model at the decoding stage. Our perturbation mechanism is model-agnostic and can be used in conjunction with any LLM. We provide theoretical analysis showing that the proposed mechanism is differentially private, and experimental results showing a privacy-utility trade-off.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Window

    cs.AI 2026-07 conditional novelty 6.0 of 10

    PANOPTICON is a synthetic benchmark of 67,718 PII-laden prompts for measuring inference-time privacy leakage in LLMs, but its realism and label accuracy are not externally validated.

  2. ISACL: Internal State Analyzer for Copyrighted Training Data Leakage

    cs.CL 2025-08 conditional novelty 5.0 of 10

    An MLP trained on LLM internal states predicts Rouge-L-defined literal copying leakage with high accuracy, but not paraphrase-level leakage.

  3. LLM Access Shield: Domain-Specific LLM Framework for Privacy Policy Compliance

    cs.CR 2025-05 conditional novelty 5.0 of 10

    An enterprise proxy that detects sensitive data in LLM prompts with a fine-tuned small model and replaces it with format-preserving encryption.

  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. Ontology- and LLM-based Data Harmonization for Federated Learning in Healthcare

    cs.LG 2025-05 conditional novelty 4.0 of 10

    An ontology-retrieval plus LLM-adjudication pipeline maps EHR outcomes to MONDO/HPO codes with 78% to 92% agreement against a human expert reviewer.

Pith tools