Paper Citation Record · LEDGER

Large Language Models Can Be Strong Differentially Private Learners

As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 29 inbound Pith citation observations for arXiv:2110.05679.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2110.05679 v6

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 29 of 29 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:50:20.230178Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T14:09:53.156936Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 875cd6b5-4a05-48e0-b6f4-c2bbbff1123f · inbound

Instance-Optimality for Private KL Distribution Estimation cites this paper.

Instance-Optimality for Private KL Distribution Estimation Large Language Models Can Be Strong Differentially Private Learners

Reference 2444

Resolution: unresolved; no resolver link, observed 2026-08-07T12:50:20.230178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 382b8d0a-7c39-420c-bdab-553eb70cf307 · inbound

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models cites this paper.

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models Large Language Models Can Be Strong Differentially Private Learners

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T05:47:30.616876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afae2c9e-5183-44da-a62a-35f4a677b2d5 · inbound

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks cites this paper.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Large Language Models Can Be Strong Differentially Private Learners

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.937446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8013d41a-81b1-42a4-bcd2-a99e88ecf4d1 · inbound

SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation cites this paper.

SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation Large Language Models Can Be Strong Differentially Private Learners

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T00:46:10.178309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71d640f6-0d1f-4b9b-ac11-125c19e8d0dc · inbound

Approximating Language Model Training Data from Weights cites this paper.

Approximating Language Model Training Data from Weights Large Language Models Can Be Strong Differentially Private Learners

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T23:59:01.305802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cfa6926-14bd-42b6-bc0a-e9b854b5262e · inbound

Memory-Efficient Differentially Private Training with Gradient Random Projection cites this paper.

Memory-Efficient Differentially Private Training with Gradient Random Projection Large Language Models Can Be Strong Differentially Private Learners

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-21T23:50:47.503777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e2e72139-bf18-4223-bf05-ec733491ff0f · inbound

FlashDP: Private Training Large Language Models with Efficient DP-SGD cites this paper.

FlashDP: Private Training Large Language Models with Efficient DP-SGD Large Language Models Can Be Strong Differentially Private Learners

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T21:06:02.499053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e5cb4a4-ee64-4fbd-acfc-4b38d7ec094c · inbound

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run cites this paper.

UniAud: A Unified Auditing Framework for High Auditing Power and Utility with One Training Run Large Language Models Can Be Strong Differentially Private Learners

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T19:55:22.389023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdf47fc5-d7e4-4472-927e-9da755c77e87 · inbound

What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests cites this paper.

What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests Large Language Models Can Be Strong Differentially Private Learners

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:33.646127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bca0c17-51cb-458a-9840-25a16c71a938 · inbound

Efficient Differentially Private Fine-Tuning of LLMs via Reinforcement Learning cites this paper.

Efficient Differentially Private Fine-Tuning of LLMs via Reinforcement Learning Large Language Models Can Be Strong Differentially Private Learners

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T11:43:13.733634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41271539-5b8b-4b94-a4cb-0c6e3febb9f0 · inbound

ISACL: Internal State Analyzer for Copyrighted Training Data Leakage cites this paper.

ISACL: Internal State Analyzer for Copyrighted Training Data Leakage Large Language Models Can Be Strong Differentially Private Learners

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T16:50:23.964756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fe18605-211b-4318-b6f4-0a55b1c79eab · inbound

When FinTech Meets Privacy: Securing Financial LLMs with Differential Private Fine-Tuning cites this paper.

When FinTech Meets Privacy: Securing Financial LLMs with Differential Private Fine-Tuning Large Language Models Can Be Strong Differentially Private Learners

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T19:55:05.931065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80b35fd5-28d7-42e0-b2f6-e71ede7e52bf · inbound

Public Data Assisted Differentially Private In-Context Learning cites this paper.

Public Data Assisted Differentially Private In-Context Learning Large Language Models Can Be Strong Differentially Private Learners

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T17:28:49.512528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62aced60-f253-4939-b246-9adcb8dc5a35 · inbound

Re-examining Low Rank adaptation for private LLM fine-tuning cites this paper.

Re-examining Low Rank adaptation for private LLM fine-tuning Large Language Models Can Be Strong Differentially Private Learners

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T13:23:19.265620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdb8a7d8-0346-4082-ab60-e33047b1b90b · inbound

Membership Inference Attacks on Tokenizers of Large Language Models cites this paper.

Membership Inference Attacks on Tokenizers of Large Language Models Large Language Models Can Be Strong Differentially Private Learners

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T11:23:16.101013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1989c850-f1e6-480a-936f-1ef20616de07 · inbound

How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy cites this paper.

How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy Large Language Models Can Be Strong Differentially Private Learners

Reference 141

Resolution: unresolved; no resolver link, observed 2026-08-03T18:52:58.492670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5107eb1e-7994-43d3-9bd7-6eaa3aa54506 · inbound

GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant cites this paper.

GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant Large Language Models Can Be Strong Differentially Private Learners

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-15T18:30:14.415235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b4eba366-56dc-44ab-a10b-fe4b9e25da0c · inbound

DP-OPD: Differentially Private On-Policy Distillation for Language Models cites this paper.

DP-OPD: Differentially Private On-Policy Distillation for Language Models Large Language Models Can Be Strong Differentially Private Learners

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:15:48.467548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2125dfab-7239-4eed-ba54-625ac101832e · inbound

DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy cites this paper.

DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy Large Language Models Can Be Strong Differentially Private Learners

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-10T08:58:12.990813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fd365312-342d-4379-9155-70a725612a22 · inbound

DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy cites this paper.

DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy Large Language Models Can Be Strong Differentially Private Learners

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-21T00:53:53.653946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8cb57c81-2fff-47b3-8ad5-9c8692b06959 · inbound

Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD? cites this paper.

Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD? Large Language Models Can Be Strong Differentially Private Learners

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:45:58.007541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5f3f9083-f27a-417d-aa39-eb0221056b6d · inbound

Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models cites this paper.

Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models Large Language Models Can Be Strong Differentially Private Learners

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-15T01:43:27.365839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cb550571-d339-4b66-9af7-88111c46c728 · inbound

DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models cites this paper.

DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models Large Language Models Can Be Strong Differentially Private Learners

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:38:19.387741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 20c522d6-f47b-42ac-9614-4c381d87c18d · inbound

Efficient DP-SGD for LLMs with Randomized Clipping cites this paper.

Efficient DP-SGD for LLMs with Randomized Clipping Large Language Models Can Be Strong Differentially Private Learners

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-06-30T12:34:39.080339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 27850c1d-cc69-41fb-b9e4-7595390ee72a · inbound

Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddings cites this paper.

Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddings Large Language Models Can Be Strong Differentially Private Learners

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-01T19:16:01.051837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a9b1d2ee-0f6b-4bdb-a305-cef663bcf4df · inbound

Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models cites this paper.

Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models Large Language Models Can Be Strong Differentially Private Learners

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:06:30.119867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e77af226-2454-4f21-bff1-d91d7c93a593 · inbound

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges cites this paper.

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges Large Language Models Can Be Strong Differentially Private Learners

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T01:27:31.066791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a25cfbe9-2448-4be0-99b7-470103bd5d79 · inbound

Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents cites this paper.

Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents Large Language Models Can Be Strong Differentially Private Learners

Reference 66

Resolution: verified exact; arxiv_id, observed 2026-07-04T14:09:53.158476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1ee23c59-407c-4471-a5bf-a1b635c93ade · inbound

Probing Memorization of Tabular In-Context Learning cites this paper.

Probing Memorization of Tabular In-Context Learning Large Language Models Can Be Strong Differentially Private Learners

Reference 51

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T09:25:40.709041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.