Paper Citation Record · LEDGER

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning

As of 16 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 2 inbound Pith citation observations for arXiv:2412.08559.

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

pith.paper-citation-record.v1
2412.08559 v3

Coverage vector

measured 65 of 65 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T17:49:46.557388Z

measured 67 of 67 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T17:20:16.735285Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

65 of 65 outbound references displayed

verified exact0
verified fuzzy25
unresolved40
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

1
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation d551e29a-8e84-4357-a6f9-0f86e5788ca9 · outbound

This paper cites write newline.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.186878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd444a7c-bff5-4a79-b46e-f22a5bda8d6e · outbound

This paper cites B., Mironov, I., Talwar, K., and Zhang, L.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning B., Mironov, I., Talwar, K., and Zhang, L

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.192983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 859671ae-4a89-4ede-a32f-15ef99c45da7 · outbound

This paper cites Evaluations of Machine Learning Privacy Defenses are Misleading.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Evaluations of Machine Learning Privacy Defenses are Misleading

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.197068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1723defe-787c-4401-953b-0e75737d4622 · outbound

This paper cites A., Jia, H., Travers, A., Zhang, B., Lie, D., and Papernot, N.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning A., Jia, H., Travers, A., Zhang, B., Lie, D., and Papernot, N

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.202427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e29bd44-47b8-4ccd-9633-f78968920af5 · outbound

This paper cites and Yang, J.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning and Yang, J

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.206888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1062693e-d77d-470b-a458-b9e83a0d537e · outbound

This paper cites The secret sharer: Evaluating and testing unintended memorization in neural networks.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning The secret sharer: Evaluating and testing unintended memorization in neural networks

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.211905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89c6aad4-3aeb-414c-825a-b54ed1450412 · outbound

This paper cites Extracting training data from large language models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Extracting training data from large language models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.221177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c268f7b-f07a-49ad-b2b7-f954924d2704 · outbound

This paper cites Membership inference attacks from first principles.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Membership inference attacks from first principles

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.225732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b136994-1b9b-4a1d-9a92-9475f2dfe0b9 · outbound

This paper cites Neural Legal Judgment Prediction in English.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Neural Legal Judgment Prediction in English

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.230793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47bb5b44-8fa7-4a85-8327-d0895d392e77 · outbound

This paper cites and Yang, D.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning and Yang, D

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:48.195044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1f5b31d9-da19-4d11-a2d2-b5bf4eea12f2 · outbound

This paper cites Efficient model updates for approximate unlearning of graph-structured data.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Efficient model updates for approximate unlearning of graph-structured data

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:48.177083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b047492a-e9e7-478f-a3bc-ace253c93cfa · outbound

This paper cites Langevin unlearning: A new perspective of noisy gradient descent for machine unlearning.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Langevin unlearning: A new perspective of noisy gradient descent for machine unlearning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.247307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2447a16-cd1c-4d3c-857f-9c34bc4404b5 · outbound

This paper cites P., Chen, Z., and Li, P.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning P., Chen, Z., and Li, P

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:48.149361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c2e7b4a2-9c8b-4107-ab1b-b2bf20adaa37 · outbound

This paper cites Do Membership Inference Attacks Work on Large Language Models?.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Do Membership Inference Attacks Work on Large Language Models?

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.258457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0134fe17-8ab0-4db6-aba0-fd7429d30233 · outbound

This paper cites and Zhang, C.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning and Zhang, C

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:48.133271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f20839d3-5a35-4998-b8d5-b96fff48a398 · outbound

This paper cites Towards Adversarial Evaluations for Inexact Machine Unlearning.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Towards Adversarial Evaluations for Inexact Machine Unlearning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.268358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6663a6ce-856d-416a-8702-04a75ed59c2a · outbound

This paper cites Eternal sunshine of the spotless net: Selective forgetting in deep networks.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Eternal sunshine of the spotless net: Selective forgetting in deep networks

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:48.111218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3fcc1e04-38bd-4eaa-a88b-812a8c24e485 · outbound

This paper cites Forgetting outside the box: Scrubbing deep networks of information accessible from input-output observations.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Forgetting outside the box: Scrubbing deep networks of information accessible from input-output observations

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:48.091185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f74c9828-d626-469e-bcac-89f8cf452cf0 · outbound

This paper cites Amnesiac machine learning.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Amnesiac machine learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.285854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eb3f584-fcdd-4f68-bcb4-58af854d05b7 · outbound

This paper cites Certified data removal from machine learning models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Certified data removal from machine learning models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:48.041748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 10b4e1f8-294d-41a3-9d4f-855878e40833 · outbound

This paper cites Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.300764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91f6130e-7599-4754-8a43-b4fd4283ab39 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning LoRA: Low-Rank Adaptation of Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.306060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1513080-9f2a-4bec-9b86-0fa1ae6a1452 · outbound

This paper cites T., Wortsman, M., Schmidt, L., Hajishirzi, H., and Farhadi, A.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning T., Wortsman, M., Schmidt, L., Hajishirzi, H., and Farhadi, A

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.312277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cf08eaa-f023-4db4-ad3f-f32878645680 · outbound

This paper cites Auditing differentially private machine learning: How private is private sgd? Advances in Neural Information Processing Systems, 33: 0 22205--22216, 2020.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Auditing differentially private machine learning: How private is private sgd? Advances in Neural Information Processing Systems, 33: 0 22205--22216, 2020

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:48.003591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 53f34a4a-4191-43af-a4fe-75487fde4389 · outbound

This paper cites Knowledge Unlearning for Mitigating Privacy Risks in Language Models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Knowledge Unlearning for Mitigating Privacy Risks in Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.322210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f53a864e-eb20-452f-99ce-2daf20add5cc · outbound

This paper cites Knowledge unlearning for mitigating privacy risks in language models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Knowledge unlearning for mitigating privacy risks in language models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.327580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2d6b065-6547-4220-9668-82fe66f54601 · outbound

This paper cites and Yang, Y.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning and Yang, Y

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.976539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ad9f16e5-e9ec-4fe6-a39a-171e92ea4d6b · outbound

This paper cites GDPR: General Data Protection Regulation (EU) 2016/679: Post-reform Personal Data Protection in the European Union.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning GDPR: General Data Protection Regulation (EU) 2016/679: Post-reform Personal Data Protection in the European Union

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.960208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 116c9480-5c8b-4e68-9fb2-baaacb938f68 · outbound

This paper cites Towards unbounded machine unlearning.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Towards unbounded machine unlearning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.942262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e97362e7-754f-4e75-a20e-f72cfc801693 · outbound

This paper cites Llm-pbe: Assessing data privacy in large language models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Llm-pbe: Assessing data privacy in large language models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.349131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c92fd73e-7161-42e3-9ac7-7fc88ec91476 · outbound

This paper cites S., Prabhu, A., and Sanyal, A.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning S., Prabhu, A., and Sanyal, A

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.355178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67612ae7-3173-4bf2-8eb7-2d29f1d8732c · outbound

This paper cites Rouge: A package for automatic evaluation of summaries.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Rouge: A package for automatic evaluation of summaries

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.361312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83dfcdb4-1de4-4764-91c0-e2d3755e39c1 · outbound

This paper cites Model sparsity can simplify machine unlearning.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Model sparsity can simplify machine unlearning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.915038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ff638570-73b1-43fb-8d68-257702baefe4 · outbound

This paper cites Rethinking Machine Unlearning for Large Language Models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Rethinking Machine Unlearning for Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.370326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4d443a0-113f-434a-b892-beb580acea5e · outbound

This paper cites Breaking the trilemma of privacy, utility, and efficiency via controllable machine unlearning.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Breaking the trilemma of privacy, utility, and efficiency via controllable machine unlearning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.888017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2e6bf036-74de-4acc-b17e-e07d754ff7f8 · outbound

This paper cites Analyzing leakage of personally identifiable information in language models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Analyzing leakage of personally identifiable information in language models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.381543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eb541fb-ce44-4b57-bbea-ee18ebb37d96 · outbound

This paper cites TOFU: A Task of Fictitious Unlearning for LLMs.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning TOFU: A Task of Fictitious Unlearning for LLMs

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.386831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34dafc4b-56b7-4bd3-bfa8-a15ff525a2d1 · outbound

This paper cites Adversary instantiation: Lower bounds for differentially private machine learning.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Adversary instantiation: Lower bounds for differentially private machine learning

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.862661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4e6515ac-86f3-4335-be5e-3b1697a64305 · outbound

This paper cites Tight auditing of differentially private machine learning.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Tight auditing of differentially private machine learning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.847639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f5b6e2bd-80af-41d2-8d15-579ef57fc102 · outbound

This paper cites Descent-to-delete: Gradient-based methods for machine unlearning.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Descent-to-delete: Gradient-based methods for machine unlearning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.403894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44cbf910-fff6-419e-9560-5cffce77815a · outbound

This paper cites Training language models to follow instructions with human feedback.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Training language models to follow instructions with human feedback

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.409015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb4582c3-426a-4468-850a-ca3ecb6cb9cb · outbound

This paper cites Z., Lu, Y., Kamath, G., Sekhari, A., and Neel, S.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Z., Lu, Y., Kamath, G., Sekhari, A., and Neel, S

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.413879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7bd5e1d-ebf0-458d-9329-360d9bdaeb77 · outbound

This paper cites In-context unlearning: Language models as few-shot unlearners.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning In-context unlearning: Language models as few-shot unlearners

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.799624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 10cdaf63-2d48-4fe9-a01a-7379f35b8acc · outbound

This paper cites Language models are unsupervised multitask learners.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Language models are unsupervised multitask learners

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.423657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation debdda0c-cd67-4b79-9062-46ffc2edc57b · outbound

This paper cites an unresolved cited work.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.428771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be5a42aa-eaca-4d2d-b2c1-b9e8d0033bd3 · outbound

This paper cites Detecting Pretraining Data from Large Language Models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Detecting Pretraining Data from Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.437139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 153ca3a1-4f08-489d-8a01-f395d8051ee8 · outbound

This paper cites Detecting pretraining data from large language models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Detecting pretraining data from large language models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.749288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 065b298f-7bc1-4c76-b6d8-e70ba4f6b894 · outbound

This paper cites MUSE: Machine Unlearning Six-Way Evaluation for Language Models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.447333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99088ac3-6abe-412e-9156-674d5c4136ff · outbound

This paper cites Membership inference attacks against machine learning models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Membership inference attacks against machine learning models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.456589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15856542-7454-4be6-8571-c61a3eed3b76 · outbound

This paper cites and Ullman, J.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning and Ullman, J

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.722616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation da59d7e3-d58b-40be-ab86-33246aa2d89d · outbound

This paper cites Privacy auditing with one (1) training run.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Privacy auditing with one (1) training run

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.701865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 90daf941-dbcf-4f54-b9dc-d9240d9a9202 · outbound

This paper cites On the necessity of auditable algorithmic definitions for machine unlearning.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning On the necessity of auditable algorithmic definitions for machine unlearning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.476685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a68c8d7a-8c1d-4385-a197-cdc47a1e67b8 · outbound

This paper cites Gradients look alike: Sensitivity is often overestimated in \ DP-SGD \.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Gradients look alike: Sensitivity is often overestimated in \ DP-SGD \

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.674470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d36e1859-3769-42de-9fb7-b09733c078d4 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.488775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51e523ab-8a39-4543-a35b-858b56e83a73 · outbound

This paper cites and Arora, R.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning and Arora, R

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.654520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8d696758-1c24-42ba-9377-298f8f7a1ee5 · outbound

This paper cites A., and Arora, R.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning A., and Arora, R

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.620111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 18bea975-49d4-4d47-b4bb-335687b31e57 · outbound

This paper cites DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.509179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c22f8e2a-0020-4901-8ae6-7c8e9c9dd053 · outbound

This paper cites Machine unlearning of pre-trained large language models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Machine unlearning of pre-trained large language models

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.566732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 590f4ac8-660c-4329-ac99-55e07a713527 · outbound

This paper cites Large language model unlearning.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Large language model unlearning

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.535019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1c57c012-f7dc-4f6f-89cd-00e26926d14f · outbound

This paper cites K., Bindschaedler, V., and Shokri, R.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning K., Bindschaedler, V., and Shokri, R

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T17:49:47.519476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 33d353ad-5cba-4ae0-8644-379b5e45489f · outbound

This paper cites Privacy risk in machine learning: Analyzing the connection to overfitting.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Privacy risk in machine learning: Analyzing the connection to overfitting

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.530710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c292f38-1c9a-4d04-b848-3878a5e11ccf · outbound

This paper cites Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.535166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9b3f024-585c-44e2-8ca5-cd0072392507 · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning OPT: Open Pre-trained Transformer Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.540196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e006c30e-3bbc-4985-8866-4631ec8f58f5 · outbound

This paper cites BERTScore: Evaluating Text Generation with BERT.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning BERTScore: Evaluating Text Generation with BERT

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.546529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e89fb69b-418b-46ed-8732-8a328bab14d7 · outbound

This paper cites What makes unlearning hard and what to do about it.

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning What makes unlearning hard and what to do about it

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-11T17:49:46.557388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 14e4024d-a23a-4d63-91b7-82e26ba857ca · inbound

Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data cites this paper.

Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:57:21.778336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4c1ee77e-6c51-4b67-a7c5-b6dbd6dde168 · inbound

Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications cites this paper.

Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning

Reference 56

Resolution: malformed identifier; arxiv_id, observed 2026-06-30T17:24:57.260154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.