Paper Citation Record · LEDGER

Eight Methods to Evaluate Robust Unlearning in LLMs

As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 45 inbound Pith citation observations for arXiv:2402.16835.

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

pith.paper-citation-record.v1
2402.16835 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 45 of 45 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T17:58:45.218633Z

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

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation e8a1823c-f786-44f6-ad72-3eafd0b1ab40 · inbound

Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods cites this paper.

Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T17:58:45.218633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dbf8d2e-8839-4cec-bc2f-736dbae5716d · inbound

Open Problems in Machine Unlearning for AI Safety cites this paper.

Open Problems in Machine Unlearning for AI Safety Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-10T21:24:10.399556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d91bc83-c5cd-45f3-8f9f-e9592643b36c · inbound

Improving LLM Unlearning Robustness via Random Perturbations cites this paper.

Improving LLM Unlearning Robustness via Random Perturbations Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.325730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 09464478-4391-473e-8841-14bc97c76f50 · inbound

Tool Unlearning for Tool-Augmented LLMs cites this paper.

Tool Unlearning for Tool-Augmented LLMs Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-09T16:44:01.280227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 454a228c-d659-4fdd-933f-f208ce6eb42d · inbound

Position: Adversarial ML for LLMs Is Not Making Any Progress cites this paper.

Position: Adversarial ML for LLMs Is Not Making Any Progress Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T12:47:21.706721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c24c5f8c-9705-45b0-b204-b9a06d97a898 · inbound

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities cites this paper.

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-09T14:47:15.221048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cef5dec4-b8d3-4e03-b3d1-38559e1168bc · inbound

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond cites this paper.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.579573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a22999c-94a0-46e0-ad4a-bc36abb9a758 · inbound

DUSK: Do Not Unlearn Shared Knowledge cites this paper.

DUSK: Do Not Unlearn Shared Knowledge Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T15:26:23.822928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d13f4b89-378c-41c3-8406-1e121e1c40df · inbound

Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs cites this paper.

Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-05-22T13:31:36.619543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2765cbc7-1e9a-44c4-8c2f-9b208adf5640 · inbound

Existing Large Language Model Unlearning Evaluations Are Inconclusive cites this paper.

Existing Large Language Model Unlearning Evaluations Are Inconclusive Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T12:05:55.328390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e6b7dd7-f26c-45f9-8206-51f47a7f8468 · inbound

Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack cites this paper.

Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T11:52:53.603231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2781febf-fda4-4eb4-bcc0-edcda9f96fee · inbound

LLM Unlearning Should Be Form-Independent cites this paper.

LLM Unlearning Should Be Form-Independent Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:33:34.723226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14620483-7a98-41d3-8f62-091906cdee59 · inbound

SoK: Machine Unlearning for Large Language Models cites this paper.

SoK: Machine Unlearning for Large Language Models Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-07T04:58:54.748386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa825a17-919c-4dcf-a4ee-b15251b88615 · inbound

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods cites this paper.

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:07.250365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5307c7e-ff97-4704-8c77-78e97c1551e8 · inbound

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs cites this paper.

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T00:29:36.619568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea4f52e7-7913-49a3-ba43-62e99b0532a1 · inbound

BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap cites this paper.

BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:01:32.243922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 978c6968-bb87-44a6-88ef-92275a37f82d · inbound

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models cites this paper.

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:56:31.579425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2c5c5b7-91af-46bc-bc00-bf47481cf5e4 · inbound

Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs cites this paper.

Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-06T19:59:52.738444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf415a3a-3e94-472a-923f-1ea5981a13af · 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 Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:33.670555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32238566-cc39-47bd-868c-dbd8e7220f39 · inbound

Do Not Mimic My Voice: Speaker Identity Unlearning for Zero-Shot Text-to-Speech cites this paper.

Do Not Mimic My Voice: Speaker Identity Unlearning for Zero-Shot Text-to-Speech Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T13:47:42.330926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd0318e0-c1f1-4481-b45c-e0443650f693 · inbound

Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection cites this paper.

Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T17:56:10.337136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52c763c6-87fe-4940-8232-20bd3358fa39 · inbound

Module-Aware Parameter-Efficient Machine Unlearning on Transformers cites this paper.

Module-Aware Parameter-Efficient Machine Unlearning on Transformers Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T17:06:12.714754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d1c0ac1-11ef-4305-b917-987005718562 · inbound

Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning cites this paper.

Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:46:16.891848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7c398949-171e-4658-96d7-5b041eccaad3 · inbound

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories cites this paper.

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:33.358328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8483f593-be0a-40b4-8705-2a866d3d73a6 · inbound

Is your algorithm unlearning or untraining? cites this paper.

Is your algorithm unlearning or untraining? Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:30:59.012199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f841165d-13b5-48cd-988b-304df86ecde0 · inbound

Efficient Unlearning through Maximizing Relearning Convergence Delay cites this paper.

Efficient Unlearning through Maximizing Relearning Convergence Delay Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T08:30:56.604294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fd593adb-5fe6-4609-a2d4-8530070c184c · inbound

Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs cites this paper.

Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T08:21:00.018926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 88058c8d-1944-47e1-8f13-05a2f2dbb99a · inbound

WIN-U: Woodbury-Informed Newton-Unlearning as a retain-free Machine Unlearning Framework cites this paper.

WIN-U: Woodbury-Informed Newton-Unlearning as a retain-free Machine Unlearning Framework Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T14:30:31.174543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d1d6e17b-826e-4795-be4e-758b17726bea · inbound

Representation-Guided Parameter-Efficient LLM Unlearning cites this paper.

Representation-Guided Parameter-Efficient LLM Unlearning Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 142

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T06:06:19.192457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9fec93fd-8154-4381-a790-777f518cb2d7 · inbound

Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance cites this paper.

Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T05:55:30.156857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9a585a78-c189-4497-af2b-a46196ef1b28 · inbound

DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning cites this paper.

DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 43

Resolution: malformed identifier; arxiv_id, observed 2026-05-09T06:10:42.147631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 97e84efd-f2c6-4984-9b94-a47f2551ec4b · inbound

DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning cites this paper.

DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 43

Resolution: malformed identifier; arxiv_id, observed 2026-05-11T01:50:51.152125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 224771bb-623b-4a19-b09b-7238f659527b · inbound

Locking Pretrained Weights via Deep Low-Rank Residual Distillation cites this paper.

Locking Pretrained Weights via Deep Low-Rank Residual Distillation Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:16:28.240944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6f634a67-74e8-48e7-ba1b-34a814217426 · inbound

Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter cites this paper.

Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:07:00.010333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2dab090c-995f-4c7b-8c82-2651e2304507 · inbound

Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning cites this paper.

Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T21:52:48.343135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8e21b990-2990-46af-a4f0-b38205b2c20a · inbound

Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries cites this paper.

Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T14:13:21.266235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dd34cfb5-a42c-443a-b12b-606080907459 · inbound

Measuring the Depth of LLM Unlearning via Activation Patching cites this paper.

Measuring the Depth of LLM Unlearning via Activation Patching Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:34:39.855279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7ccfb302-3dd1-422f-94db-17e7c20537a5 · inbound

Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility cites this paper.

Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:06:30.396031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9b042b5b-81dc-4716-a16a-d3ec83838044 · inbound

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

RepSelect: Robust LLM Unlearning via Representation Selectivity Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T17:58:47.239934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 41e88a88-1f60-4c55-8ce4-57d776ed3cca · inbound

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models cites this paper.

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 103

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T20:08:55.576901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3c7c239a-f7af-49a2-99fa-8393385898ff · inbound

Position: The Term "Machine Unlearning" Is Overused in LLMs cites this paper.

Position: The Term "Machine Unlearning" Is Overused in LLMs Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T13:25:44.911576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8888c868-11a5-4c60-8a99-7de2a31183be · inbound

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem cites this paper.

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-13T04:30:23.082717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 911b0ced-9238-476e-bee8-7b64758dd8f9 · inbound

Understanding Machine Unlearning Through the Lens of Mode Connectivity cites this paper.

Understanding Machine Unlearning Through the Lens of Mode Connectivity Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-31T23:27:28.211990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d83ad0b-9b84-4acb-8e24-0f6db23e9f82 · inbound

Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration cites this paper.

Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T00:35:50.151033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45632c32-b47d-4a4b-9a55-74c1b203f729 · inbound

Suppression Sticks, Locality Is Fragile: A Closed-Loop Target-and-Control Audit of Task-Vector Negation in VLA Policies cites this paper.

Suppression Sticks, Locality Is Fragile: A Closed-Loop Target-and-Control Audit of Task-Vector Negation in VLA Policies Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T18:54:46.557292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.