Paper Citation Record · LEDGER

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

As of 9 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 14 inbound Pith citation observations for arXiv:2502.05374.

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

pith.paper-citation-record.v1
2502.05374 v4

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T19:40:31.637079Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 14 of 14 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T13:54:39.597195Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T20:07:21.193836Z

Reference resolution

31 of 31 outbound references displayed

verified exact1
verified fuzzy4
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 612f1543-1877-437e-9897-df9cef8a646a · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Measuring Massive Multitask Language Understanding

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.560219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d09ef9e6-89cb-4a54-b129-dce1425d6704 · outbound

This paper cites Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.563392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f68ace7d-44b0-4e01-8a58-bf701b02571d · outbound

This paper cites Averaging Weights Leads to Wider Optima and Better Generalization.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Averaging Weights Leads to Wider Optima and Better Generalization

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.566572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d4d4c01-9df2-43ef-90d3-3fdd4b514194 · outbound

This paper cites Advancing the Robustness of Large Language Models through Self-Denoised Smoothing.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Advancing the Robustness of Large Language Models through Self-Denoised Smoothing

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.573098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b6ae6d0-1ab0-4c7e-990d-dc7891646bb9 · outbound

This paper cites Large Language Model Unlearning via Embedding-Corrupted Prompts.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Large Language Model Unlearning via Embedding-Corrupted Prompts

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.576262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

This paper cites Eight Methods to Evaluate Robust Unlearning in LLMs.

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 5cb42ed6-2e07-4310-b48b-12482eb6e795 · outbound

This paper cites On First-Order Meta-Learning Algorithms.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond On First-Order Meta-Learning Algorithms

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.582487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55289d4d-4c9c-439c-96e5-814274229821 · outbound

This paper cites In-Context Unlearning: Language Models as Few Shot Unlearners.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond In-Context Unlearning: Language Models as Few Shot Unlearners

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.585388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cb99fd5-a8cd-40ec-bcd0-bf54ca4d89eb · outbound

This paper cites Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.588552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddfc1d88-f0b5-441c-8aca-648ac6319223 · outbound

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

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.592118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b7b9fe4-c404-4f6c-adc4-0bbb03264506 · outbound

This paper cites UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.595781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 728cddfa-dacd-4def-8f48-5f7ca751ab98 · outbound

This paper cites D., Ng, A.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond D., Ng, A

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:40:32.007648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d14fe7cb-8000-4d62-b231-4c737272723d · outbound

This paper cites Guardrail Baselines for Unlearning in LLMs.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Guardrail Baselines for Unlearning in LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.605132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 699624d0-e224-4a34-899b-e2277283da81 · outbound

This paper cites FLRT: Fluent Student-Teacher Redteaming.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond FLRT: Fluent Student-Teacher Redteaming

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.608351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27076dde-4d45-476e-844e-eb1d5513aef3 · outbound

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

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.614403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da70c45c-ff2a-473c-9d15-d563af8ae01a · outbound

This paper cites Weight perturbation as defense against adversarial word substitutions.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Weight perturbation as defense against adversarial word substitutions

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:40:31.997534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f51a3c09-5b23-4890-9ec3-fc74d08d7713 · outbound

This paper cites Large Language Model Unlearning.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Large Language Model Unlearning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.621100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 301255c3-3890-45ac-b042-e5dc5d703fab · outbound

This paper cites On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-08T19:40:31.681095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cdc3ec2b-52e3-42e2-acb2-c92ee5ac074e · outbound

This paper cites On the Duality Between Sharpness-Aware Minimization and Adversarial Training.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond On the Duality Between Sharpness-Aware Minimization and Adversarial Training

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.627559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ecf2133-9494-4744-8f51-8b9a3e66e9ed · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.630851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59d2c78b-f59d-4b5a-acc6-59b66a0fd6b8 · outbound

This paper cites an unresolved cited work.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-08T19:40:31.987438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation def0b735-8cca-43c4-8be5-78ced75bb941 · outbound

This paper cites For the Books dataset, we utilize ICLM 7B, fine-tuned on the Harry Potter books.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond For the Books dataset, we utilize ICLM 7B, fine-tuned on the Harry Potter books

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:40:31.977395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5993d233-5c97-45ba-b019-6bfcebac0fa6 · outbound

This paper cites Tamper-Resistant Safeguards for Open-Weight LLMs.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Tamper-Resistant Safeguards for Open-Weight LLMs

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.602077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e99b886a-d901-4c02-b30d-b043d6186b0c · outbound

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

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Knowledge Unlearning for Mitigating Privacy Risks in Language Models

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.570140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdcbd7fb-7ce3-4f32-bfa1-7d6d90916163 · outbound

This paper cites Visualizing and Understanding the Effectiveness of BERT.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Visualizing and Understanding the Effectiveness of BERT

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.556829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37555eb5-c1cd-4926-9016-55a23c4ae9ac · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Training Verifiers to Solve Math Word Problems

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.545888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7bc7319-be6b-497a-a1ef-e632752e9050 · outbound

This paper cites Sharpness-Aware Minimization Alone can Improve Adversarial Robustness.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Sharpness-Aware Minimization Alone can Improve Adversarial Robustness

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.611449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fae7a7fe-e69d-49e7-90ba-8be2118fb806 · outbound

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

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Open Problems in Machine Unlearning for AI Safety

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.538686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2b4145f-fcee-4283-8540-783f80a24eb0 · outbound

This paper cites Simplicity prevails: Rethinking negative pref- erence optimization for llm unlearning.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Simplicity prevails: Rethinking negative pref- erence optimization for llm unlearning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.553189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e026bcf2-e946-49b4-a975-57a13b8833d5 · outbound

This paper cites Do Unlearning Methods Remove Information from Language Model Weights?.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond Do Unlearning Methods Remove Information from Language Model Weights?

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T19:40:31.549295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c8d618d-385f-44a2-b303-43cda6c8c65f · outbound

This paper cites and Yang, J.

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond and Yang, J

Reference 2025

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T19:40:32.017634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

Observation 96f2d857-7d42-450c-9f52-a4256fff3063 · inbound

A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction cites this paper.

A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T13:54:39.597195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0028ab0-70e5-42c8-aa8d-6fab9f174cdd · inbound

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

Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:46:17.126942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation baec5ee2-7527-47d8-86f8-be60b8bc359f · inbound

Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding cites this paper.

Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T23:39:05.091763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4672d14-3c18-4119-9aed-c9a3155faf7e · inbound

A Mechanistic Perspective and Circuit-Guided Difficulty Metric for Unlearning cites this paper.

A Mechanistic Perspective and Circuit-Guided Difficulty Metric for Unlearning Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T10:37:00.505705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9d51c13-3af9-4581-903d-91401588614b · inbound

CURE:Circuit-Aware Unlearning for LLM-based Recommendation cites this paper.

CURE:Circuit-Aware Unlearning for LLM-based Recommendation Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-13T16:48:02.702494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0542f4da-eb24-4f04-a9a3-409c50cd9583 · inbound

A Numerical PDEs Approach to Evolution Equations in Shape Analysis Based on Regularized Morphoelasticity cites this paper.

A Numerical PDEs Approach to Evolution Equations in Shape Analysis Based on Regularized Morphoelasticity Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T12:04:13.336341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22a74234-2753-4ed1-9408-5aae69c5b456 · inbound

Efficient Unlearning through Maximizing Relearning Convergence Delay cites this paper.

Efficient Unlearning through Maximizing Relearning Convergence Delay Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:30:56.577842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7ed1d545-3f53-4970-9a98-ec7d678047db · inbound

One Step to the Side: Why Defenses Against Malicious Finetuning Fail Under Adaptive Adversaries cites this paper.

One Step to the Side: Why Defenses Against Malicious Finetuning Fail Under Adaptive Adversaries Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-06-30T21:05:04.058445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d1c62547-500c-4c05-9b81-11151dd56fb8 · inbound

BARRIER: Bounded Activation Regions for Robust Information Erasure cites this paper.

BARRIER: Bounded Activation Regions for Robust Information Erasure Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:18:54.702131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 011b2cb6-9d87-4316-aa80-dd30117b79c0 · inbound

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

Measuring the Depth of LLM Unlearning via Activation Patching Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:34:40.189857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 46a2a673-a505-484a-acce-7abcbd568720 · inbound

TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation cites this paper.

TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-02T20:07:21.195871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e592eb6e-c3db-40f5-ab67-07e50cd110fd · inbound

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats cites this paper.

LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 120

Resolution: unresolved; no resolver link, observed 2026-08-02T10:25:19.920395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4302c2c-2f46-42f0-bf67-10cf3bde04e7 · inbound

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

Understanding Machine Unlearning Through the Lens of Mode Connectivity Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-31T23:27:26.144256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fbfe937-109d-4674-be52-26d3e5097bbd · 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 Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T00:35:49.649177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.