Extracting Training Data from Large Language Models | Paper Citation Record

Observation 1f249adc-febb-4812-a104-ac684d731332 · inbound

The Pile: An 800GB Dataset of Diverse Text for Language Modeling cites this paper.

The Pile: An 800GB Dataset of Diverse Text for Language Modeling Extracting Training Data from Large Language Models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-10T21:35:18.749655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a001a767-4dd2-40a8-909e-e78e492c4507 · inbound

Deduplicating Training Data Makes Language Models Better cites this paper.

Deduplicating Training Data Makes Language Models Better Extracting Training Data from Large Language Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-24T13:39:31.714001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5d360aae-b923-4573-b2ad-60a12b397e5b · inbound

Ethical and social risks of harm from Language Models cites this paper.

Ethical and social risks of harm from Language Models Extracting Training Data from Large Language Models

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:24:29.952856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3da7c7d4-035e-4215-a99a-aa3bd6df49c2 · inbound

LaMDA: Language Models for Dialog Applications cites this paper.

LaMDA: Language Models for Dialog Applications Extracting Training Data from Large Language Models

Reference 73

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T03:17:32.518336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0e12e445-3aea-4195-bc41-e52d725cb488 · inbound

Quantifying Memorization Across Neural Language Models cites this paper.

Quantifying Memorization Across Neural Language Models Extracting Training Data from Large Language Models

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T22:04:59.731563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 78f2a4f4-10c0-4085-a8cd-f4364edeca01 · inbound

Scaling Laws and Interpretability of Learning from Repeated Data cites this paper.

Scaling Laws and Interpretability of Learning from Repeated Data Extracting Training Data from Large Language Models

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T15:52:40.461771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 862123b6-3250-4082-8f30-c978da3b3fc5 · inbound

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned cites this paper.

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned Extracting Training Data from Large Language Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-12T01:38:08.468054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 54ae7179-ff65-4628-80c9-4d5bd6586ed9 · inbound

MusicLM: Generating Music From Text cites this paper.

MusicLM: Generating Music From Text Extracting Training Data from Large Language Models

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T14:27:06.256783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ae0ef567-9f81-41fc-a125-e94baeaec035 · inbound

Industry Practitioners Perspectives on AI Model Quality: Perceptions, Challenges, and Solutions cites this paper.

Industry Practitioners Perspectives on AI Model Quality: Perceptions, Challenges, and Solutions Extracting Training Data from Large Language Models

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-24T04:23:52.895916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8fd242df-c7e3-41f4-83a3-3354df4306fa · inbound

ORPO: Monolithic Preference Optimization without Reference Model cites this paper.

ORPO: Monolithic Preference Optimization without Reference Model Extracting Training Data from Large Language Models

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-16T09:34:04.740850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 791924ef-9c4a-4656-b0f7-6e84274e76fc · inbound

A Social Outcomes and Priorities centered (SOP) Framework for AI policy cites this paper.

A Social Outcomes and Priorities centered (SOP) Framework for AI policy Extracting Training Data from Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T21:51:05.639460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d60d1838-244d-47d7-b20c-fca6d297796d · inbound

Detecting Memorization in Large Language Models cites this paper.

Detecting Memorization in Large Language Models Extracting Training Data from Large Language Models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-12T04:50:15.626636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e37d055d-91eb-41eb-967c-83c4a0bf7aa9 · inbound

Trust & Safety of LLMs and LLMs in Trust & Safety cites this paper.

Trust & Safety of LLMs and LLMs in Trust & Safety Extracting Training Data from Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T23:52:33.159458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07b45183-d87e-42d3-aee1-ba78389b23f1 · inbound

Towards the Anonymization of the Language Modeling cites this paper.

Towards the Anonymization of the Language Modeling Extracting Training Data from Large Language Models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-23T06:32:39.434987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 62fcb607-fd74-4d3c-ad40-67c0d7f50894 · inbound

LIMO: Less is More for Reasoning cites this paper.

LIMO: Less is More for Reasoning Extracting Training Data from Large Language Models

Reference 253

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T02:11:37.303275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 73256e9c-8ad7-463d-8010-e673d7e5b027 · inbound

Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning cites this paper.

Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning Extracting Training Data from Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:25.072025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65626d80-068e-4c69-a336-5968e501f862 · inbound

Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation cites this paper.

Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation Extracting Training Data from Large Language Models

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-22T01:34:30.348594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 63487873-dc3e-4722-88fe-87cac685c658 · inbound

Approximating Language Model Training Data from Weights cites this paper.

Approximating Language Model Training Data from Weights Extracting Training Data from Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T23:58:58.403904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 337899db-b046-4a2b-9411-196bf7d67a2e · inbound

From Teacher to Student: Tracking Memorization Through Model Distillation cites this paper.

From Teacher to Student: Tracking Memorization Through Model Distillation Extracting Training Data from Large Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:10.559721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42bf4c06-3c92-4a00-9aa0-b9d9be79d119 · inbound

Low-Perplexity LLM-Generated Sequences and Where To Find Them cites this paper.

Low-Perplexity LLM-Generated Sequences and Where To Find Them Extracting Training Data from Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T20:44:58.634485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ea55d67-c336-4e53-831c-47d55a3e9ae5 · inbound

Model Inversion Attacks on Llama 3: Extracting PII from Large Language Models cites this paper.

Model Inversion Attacks on Llama 3: Extracting PII from Large Language Models Extracting Training Data from Large Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T19:48:55.141023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e941e346-f608-4269-aa6c-193a4c956cbc · inbound

Adversarial Machine Learning Attacks on Financial Reporting via Maximum Violated Multi-Objective Attack cites this paper.

Adversarial Machine Learning Attacks on Financial Reporting via Maximum Violated Multi-Objective Attack Extracting Training Data from Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T19:31:00.983161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77948df8-f2ae-4a6a-9eeb-3f0a4ab7d5c2 · inbound

On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance cites this paper.

On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance Extracting Training Data from Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:00.426132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa9c0ed5-5f41-4d48-941c-dccbe7fe0fdc · inbound

AnalogFed: Privacy-Preserving Discovery of Analog Circuits at Scale with Federated Generative AI cites this paper.

AnalogFed: Privacy-Preserving Discovery of Analog Circuits at Scale with Federated Generative AI Extracting Training Data from Large Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T15:46:55.618154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45843fde-c633-4720-a317-5c86e2576e11 · inbound

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation cites this paper.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Extracting Training Data from Large Language Models

Reference 118

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:43.822425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd504875-9749-41af-a9f8-8cfebb784e8d · inbound

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

ISACL: Internal State Analyzer for Copyrighted Training Data Leakage Extracting Training Data from Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T16:50:19.605008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a4074d2-053f-4fce-b7a7-fa03fb5fe38e · inbound

Evaluating Differentially Private Generation of Domain-Specific Text cites this paper.

Evaluating Differentially Private Generation of Domain-Specific Text Extracting Training Data from Large Language Models

Reference 2650

Resolution: unresolved; no resolver link, observed 2026-08-05T15:09:03.247046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 178f3650-d0a3-4e33-8ccd-087eef77de7b · inbound

Preventing Another Tessa: Modular Safety Middleware For Health-Adjacent AI Assistants cites this paper.

Preventing Another Tessa: Modular Safety Middleware For Health-Adjacent AI Assistants Extracting Training Data from Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T04:46:41.159734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffe1c536-0a58-4f78-b42e-25b0318b13be · inbound

SynBench: A Benchmark for Differentially Private Text Generation cites this paper.

SynBench: A Benchmark for Differentially Private Text Generation Extracting Training Data from Large Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-18T16:46:37.468783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1b70cc15-f9fc-40f1-864b-0fc5c61e68b4 · inbound

When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation cites this paper.

When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation Extracting Training Data from Large Language Models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-16T23:48:41.851547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a00801a1-c0c0-4373-9b48-aa540bf3dae9 · inbound

Swiss-Bench 003: Evaluating LLM Reliability and Adversarial Security for Swiss Regulatory Contexts cites this paper.

Swiss-Bench 003: Evaluating LLM Reliability and Adversarial Security for Swiss Regulatory Contexts Extracting Training Data from Large Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:35:48.805002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6dc63095-16dc-4a9c-bda3-7ae3027a0fea · inbound

Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies cites this paper.

Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies Extracting Training Data from Large Language Models

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T22:34:07.373969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5b4fee91-8675-4ad1-9c0a-12203b86194f · inbound

A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework cites this paper.

A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework Extracting Training Data from Large Language Models

Reference 66

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:51:09.389604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 89517f86-bac3-429d-b231-14029185edba · inbound

Making AI-Assisted Grant Evaluation Auditable without Exposing the Model cites this paper.

Making AI-Assisted Grant Evaluation Auditable without Exposing the Model Extracting Training Data from Large Language Models

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T23:51:17.879632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4f74794c-9c4d-4e90-b0d3-ef5718da6854 · inbound

Dataset Watermarking for Closed LLMs with Provable Detection cites this paper.

Dataset Watermarking for Closed LLMs with Provable Detection Extracting Training Data from Large Language Models

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T05:00:57.288375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 57b34014-a152-497f-914f-558789c1199b · inbound

LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems cites this paper.

LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems Extracting Training Data from Large Language Models

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-22T05:01:05.960115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f9fbb4f0-4061-4a72-9d45-69a78e5d0c7e · inbound

Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing cites this paper.

Reading the Finetuning Prior: Verbatim Content Recovery via Contrastive Decoding Diffing Extracting Training Data from Large Language Models

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T22:44:01.664060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 40c45581-7f6a-4603-a973-ad6231aaf9b3 · inbound

MRMMIA: Membership Inference Attacks on Memory in Chat Agents cites this paper.

MRMMIA: Membership Inference Attacks on Memory in Chat Agents Extracting Training Data from Large Language Models

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T12:13:27.072292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d64b9315-cf10-4cbb-b788-e426d461e0a9 · inbound

Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing cites this paper.

Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing Extracting Training Data from Large Language Models

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T23:56:23.234607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1468ffd0-0d5b-4fbc-8846-251fc95b7cbf · inbound

Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails cites this paper.

Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails Extracting Training Data from Large Language Models

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:26:57.057543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 80ad5aa8-0703-40ed-8ccb-81d3bd7d3de1 · inbound

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs cites this paper.

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs Extracting Training Data from Large Language Models

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:56:57.468052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f30c694f-27ce-46d4-9fc0-2cd79110ae11 · inbound

MC-PDD: Masked Corpus-Level Pretraining Data Detection for Black-Box Large Language Models cites this paper.

MC-PDD: Masked Corpus-Level Pretraining Data Detection for Black-Box Large Language Models Extracting Training Data from Large Language Models

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T20:57:23.357949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b6dac66e-c769-457e-8edf-e64ccde2034f · inbound

Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs cites this paper.

Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs Extracting Training Data from Large Language Models

Reference 88

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T01:07:30.231259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e2d36494-b0a8-4b0d-8507-d9c8ae0a36cb · inbound

The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans cites this paper.

The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans Extracting Training Data from Large Language Models

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T09:05:36.687299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 48cfd250-1281-4f89-a3b2-72bd4189fdcf · inbound

OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents cites this paper.

OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents Extracting Training Data from Large Language Models

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T11:58:06.926713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation fb4f126f-1954-4a98-80d7-4e31d24dede2 · inbound

RepSelect: Robust LLM Unlearning via Representation Selectivity cites this paper.

RepSelect: Robust LLM Unlearning via Representation Selectivity Extracting Training Data from Large Language Models

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T17:58:47.182482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 99fef884-5b0d-4d97-9e02-13ed9e2c4cf6 · inbound

Exposing the Illusion of Erasure in Knowledge Editing for LLMs cites this paper.

Exposing the Illusion of Erasure in Knowledge Editing for LLMs Extracting Training Data from Large Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-04T10:09:44.276219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ec1a872e-ec30-4beb-b1a3-9eb6d7dd83c7 · 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 Extracting Training Data from Large Language Models

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-07-04T14:09:53.281660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ffdbb1a8-433a-472a-900d-5d4097d0fa7d · inbound

AI Native Games: A Survey and Roadmap cites this paper.

AI Native Games: A Survey and Roadmap Extracting Training Data from Large Language Models

Reference 86

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:06:58.758903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4d8c8d02-19f8-4a42-88a7-cde6e538eab4 · inbound

AI Native Games: A Survey and Roadmap cites this paper.

AI Native Games: A Survey and Roadmap Extracting Training Data from Large Language Models

Reference 86

Resolution: unresolved; no resolver link, observed 2026-07-12T09:30:07.729486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41d6405e-1aa9-43f1-8a6a-e244df868e0e · inbound

Auditing Forgetting in Limited Memory Language Models cites this paper.

Auditing Forgetting in Limited Memory Language Models Extracting Training Data from Large Language Models

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-02T13:16:58.312170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 724b7aaa-782d-4928-b56a-e74cdf712e32 · inbound

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification cites this paper.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Extracting Training Data from Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.482286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c1c3df4-b145-41bb-a08f-62af760ed21c · inbound

DECAF: De-Clustering for Adaptive Representational Unlearning cites this paper.

DECAF: De-Clustering for Adaptive Representational Unlearning Extracting Training Data from Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T23:33:49.808882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c08c5f00-e512-4bec-91e8-c1bbee4adaf8 · inbound

Bits and Memories: Measuring Verbatim Extraction Across LLM Quantization cites this paper.

Bits and Memories: Measuring Verbatim Extraction Across LLM Quantization Extracting Training Data from Large Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:36.726398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers