Paper Citation Record · LEDGER

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection

As of 16 August 2026, this Paper Citation Record lists 100 of 110 outbound references and 6 inbound Pith citation observations for arXiv:2505.13312.

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

pith.paper-citation-record.v1
2505.13312 v1

Coverage vector

measured 100 of 110 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:21:39.947423Z

measured 106 of 106 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 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:17:57.144501Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T19:03:51.460176Z

Reference resolution

100 of 110 outbound references displayed

verified exact2
verified fuzzy1
unresolved97
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 59830744-7cdf-417c-940a-795affc8ee24 · outbound

This paper cites GPT-4 Technical Report.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.556543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cd35024-e9e8-46df-a7b3-5a203f871fbc · outbound

This paper cites Harnessing Business and Media Insights with Large Language Models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Harnessing Business and Media Insights with Large Language Models

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-15T20:21:41.016965Z

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 4da7e7ef-2787-48a5-ba27-6211cc0ed0f5 · outbound

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

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Open Problems in Machine Unlearning for AI Safety

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.566982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd5b10f9-d16d-435a-b6eb-61ddea204b5c · outbound

This paper cites Soft Prompting for Unlearning in Large Language Models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Soft Prompting for Unlearning in Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.571160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c272b9c-5431-469d-b45a-13d6625f97df · outbound

This paper cites Piqa: Reasoning about physical commonsense in natural language.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Piqa: Reasoning about physical commonsense in natural language

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.575365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9669de93-0ac9-4921-affa-042c0cb34eec · outbound

This paper cites Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.579134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4774f3e-2d5e-49dc-ae80-f660ba121b6e · outbound

This paper cites Towards making systems forget with machine unlearning.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Towards making systems forget with machine unlearning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.583475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d926f621-11f4-4fa1-a6e9-03f91be9c50d · outbound

This paper cites Extracting training data from large language models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Extracting training data from large language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.587034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63cac78f-caec-4c7c-b3ef-4849c6991a1a · outbound

This paper cites Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.590621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e67c9252-53d6-460f-ae8c-93dd78e8d000 · outbound

This paper cites Unlearn What You Want to Forget: Efficient Unlearning for LLMs.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Unlearn What You Want to Forget: Efficient Unlearning for LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.594390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 795a1b16-4cf5-4f8c-8d6c-81c19f67d745 · outbound

This paper cites Safeeraser: Enhancing safety in multimodal large language models through multimodal machine unlearning.arXiv preprint arXiv:2502.12520, 2025.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Safeeraser: Enhancing safety in multimodal large language models through multimodal machine unlearning.arXiv preprint arXiv:2502.12520, 2025

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.598404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78324e51-e8a5-4995-8ba7-5522c410350c · outbound

This paper cites On the Measure of Intelligence.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection On the Measure of Intelligence

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.602071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f22c080-3620-45a1-bd69-6304a2868fcb · outbound

This paper cites How to protect copyright data in optimization of large language models? InProceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 17871–17879, 2024.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection How to protect copyright data in optimization of large language models? InProceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 17871–17879, 2024

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.605851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57363400-a85a-4127-8497-fd062178bb27 · outbound

This paper cites AI Safety in Generative AI Large Language Models: A Survey.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection AI Safety in Generative AI Large Language Models: A Survey

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.609549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04644530-9b6a-4396-b69d-f53967498be5 · outbound

This paper cites BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.613574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e070968-4e64-4626-b0a2-548efa6199f6 · outbound

This paper cites The pascal recognising textual entailment challenge.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection The pascal recognising textual entailment challenge

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.617093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4b2f4a3-e683-44c6-bde9-755c4c66a25a · outbound

This paper cites Security and privacy challenges of large language models: A survey.ACM Computing Surveys, 57(6):1–39, 2025.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Security and privacy challenges of large language models: A survey.ACM Computing Surveys, 57(6):1–39, 2025

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.620782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84359218-d36b-4e41-951e-b04eaef1400e · outbound

This paper cites Adversarial Machine Unlearning.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Adversarial Machine Unlearning

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-15T20:21:40.859684Z

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 cd00f7dc-2756-4d40-9bc0-bb807867eb94 · outbound

This paper cites Label Smoothing Improves Machine Unlearning.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Label Smoothing Improves Machine Unlearning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.627986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de8b167c-7078-4cd0-bb9d-fe1092dffd6d · outbound

This paper cites Unified Parameter-Efficient Unlearning for LLMs.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Unified Parameter-Efficient Unlearning for LLMs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.632001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 837101bf-a743-4538-ad67-b0e4f0518cb1 · outbound

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

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.635552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42509284-e13c-4b5b-87d7-4d0566ba7f2b · outbound

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

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Do Membership Inference Attacks Work on Large Language Models?

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.639005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce9b0b8b-1dff-4fd6-915e-096a97adefcf · outbound

This paper cites Who's Harry Potter? Approximate Unlearning in LLMs.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Who's Harry Potter? Approximate Unlearning in LLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.643116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a0788e1-329f-4771-81ef-bccff379a19b · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection KTO: Model Alignment as Prospect Theoretic Optimization

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.646965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9640f48a-7dc5-4ec0-a09b-3e5ba29a4bbe · outbound

This paper cites General data protection regulation (gdpr).

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection General data protection regulation (gdpr)

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.650766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c5b9907-cbbb-4e22-ab34-27a97f9a87e1 · outbound

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

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.655060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation babe65c6-c9ad-40f1-acc4-81cff5d1cb7a · outbound

This paper cites Challenging forgets: Unveiling the worst-case forget sets in machine unlearning.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Challenging forgets: Unveiling the worst-case forget sets in machine unlearning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.659032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae4d99af-86e4-4e28-97db-a2e9e87111f7 · outbound

This paper cites Simplicity prevails: Rethinking negative preference optimization for llm unlearning.arXiv preprint arXiv:2410.07163, 2024.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Simplicity prevails: Rethinking negative preference optimization for llm unlearning.arXiv preprint arXiv:2410.07163, 2024

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.662611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94448519-80bc-4577-b1ba-95377946d51a · outbound

This paper cites SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.666199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c34afa4d-9f93-4265-aa69-ea7cebef6afe · outbound

This paper cites On Large Language Model Continual Unlearning.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection On Large Language Model Continual Unlearning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.670473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f16bec1a-cbcf-49ae-a2c7-168bf07281fe · outbound

This paper cites The Llama 3 Herd of Models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection The Llama 3 Herd of Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.674724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 162d452f-c133-45f9-9e61-ef953f0ce1b8 · outbound

This paper cites The times sues openai and microsoft over ai use of copyrighted work.The New York Times, 27, 2023.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection The times sues openai and microsoft over ai use of copyrighted work.The New York Times, 27, 2023

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.678446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03cb774f-e99b-4dc3-9c49-b3df6648b284 · outbound

This paper cites MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.682213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf50a7f0-1072-40c0-a4dd-9550f160c0e7 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.687052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58569e69-6e24-4ef9-abe3-00d0c911c610 · outbound

This paper cites news-please - a generic news crawler and extractor.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection news-please - a generic news crawler and extractor

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.690939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1ebcff5-35a3-45cd-8d92-14ec835ff773 · outbound

This paper cites Risk and Response in Large Language Models: Evaluating Key Threat Categories.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Risk and Response in Large Language Models: Evaluating Key Threat Categories

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.694584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79bb6542-fa72-47d8-b057-2c135af6338b · outbound

This paper cites MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.698337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c24270b-13b6-487a-b5f0-e92186600cec · outbound

This paper cites Editing Models with Task Arithmetic.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Editing Models with Task Arithmetic

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.702400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84045de5-f00d-41b5-883b-1d39308d109e · outbound

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

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Knowledge Unlearning for Mitigating Privacy Risks in Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.707245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88845c75-1d97-44d3-b94a-001dad3ac8a1 · outbound

This paper cites Reversing the forget-retain objectives: An efficient llm unlearning framework from logit difference.Advances in Neural Information Processing Systems, 37:12581–12611, 2024.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Reversing the forget-retain objectives: An efficient llm unlearning framework from logit difference.Advances in Neural Information Processing Systems, 37:12581–12611, 2024

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.711423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a56ff115-db5d-4c13-b7ed-51e1a4ed5df8 · outbound

This paper cites Model sparsity can simplify machine unlearning.Advances in Neural Information Processing Systems, 36:51584–51605, 2023.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Model sparsity can simplify machine unlearning.Advances in Neural Information Processing Systems, 36:51584–51605, 2023

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.715201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0395c996-c3d9-4284-b592-cc1e441ddd04 · outbound

This paper cites WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.718875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bce8cd3-759a-419a-aa05-8259dd49bfc1 · outbound

This paper cites SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.723036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16904a84-8cce-4e4b-bbda-ba6b0b03d3ba · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.726819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23c23a87-23dd-4613-992a-29cfc6ec8d99 · outbound

This paper cites Copyright Violations and Large Language Models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Copyright Violations and Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.730672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17678326-0258-4c81-8131-760815dfba94 · outbound

This paper cites Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.734390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e3927f4-7f40-404b-9088-1e221bb46c0b · outbound

This paper cites RACE: Large-scale ReAding Comprehension Dataset From Examinations.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection RACE: Large-scale ReAding Comprehension Dataset From Examinations

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.738654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d5f37e4-8ef1-4e69-a877-c36b5c774f10 · outbound

This paper cites Textbooks Are All You Need II: phi-1.5 technical report.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Textbooks Are All You Need II: phi-1.5 technical report

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.742286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bda671ae-0d82-4431-9cb8-d2a5da076362 · outbound

This paper cites LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.746110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7cb8c9e-d472-4ead-8982-7756e303457b · outbound

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

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Rouge: A package for automatic evaluation of summaries

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.750058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b10c6e58-420e-4515-8901-bf9716b9e7a6 · outbound

This paper cites TruthfulQA: Measuring How Models Mimic Human Falsehoods.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection TruthfulQA: Measuring How Models Mimic Human Falsehoods

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.753800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 501f7b88-fab1-4d67-bfe5-ee13f4ed1b1e · outbound

This paper cites Continual learning and private unlearning.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Continual learning and private unlearning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.757639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8089cb9-5de1-4a34-aaff-d1ee756e1523 · outbound

This paper cites Large language model unlearning via embedding-corrupted prompts.Advances in Neural Information Processing Systems, 37:118198–118266, 2024.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Large language model unlearning via embedding-corrupted prompts.Advances in Neural Information Processing Systems, 37:118198–118266, 2024

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.761302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe36371e-b580-4183-9a4b-93ca1b0d6d88 · outbound

This paper cites Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.765014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a748563d-be7f-4703-ba3b-4c37df9805d8 · outbound

This paper cites Rethinking machine unlearning for large language models.Nature Machine Intelligence, pages 1–14, 2025.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Rethinking machine unlearning for large language models.Nature Machine Intelligence, pages 1–14, 2025

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.769505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e3977c3-4a62-42be-b086-cb3e2577124a · outbound

This paper cites Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.772952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f636834a-8c06-42ab-9bdb-0c94d52890f3 · outbound

This paper cites On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writing.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writing

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.776733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ed40bcb-92dc-4cc2-9c87-6f7b96ae5d14 · outbound

This paper cites Decoupled Weight Decay Regularization.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Decoupled Weight Decay Regularization

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.780492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf1ae6c6-7723-4cdc-b08b-417e90cea1b1 · outbound

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

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Eight Methods to Evaluate Robust Unlearning in LLMs

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.784884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0828432f-d54c-47a7-9a97-d7328c564cb3 · outbound

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

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection TOFU: A Task of Fictitious Unlearning for LLMs

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.788944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ff95b63-54f9-43d7-91dc-b8ec4906bb1a · outbound

This paper cites Llm dataset inference: Did you train on my dataset?Advances in Neural Information Processing Systems, 37:124069– 124092, 2024.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Llm dataset inference: Did you train on my dataset?Advances in Neural Information Processing Systems, 37:124069– 124092, 2024

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.792867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 617b9275-e143-4565-9f3d-df1baf3259f9 · outbound

This paper cites Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.796331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edc72172-c8ae-40ed-8382-a9409496ee30 · outbound

This paper cites Pointer Sentinel Mixture Models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Pointer Sentinel Mixture Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.802037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f6d2854-2598-4d37-9427-d97843bbc75d · outbound

This paper cites Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.806132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a83c2b9-daa0-4ad9-ace8-4dc9882ef711 · outbound

This paper cites Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.809889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fde59b03-eb54-481d-9487-bad9bd347b4b · outbound

This paper cites Quantifying the privacy risks of learning high-dimensional graphical models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Quantifying the privacy risks of learning high-dimensional graphical models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.814010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f559cfc0-ce9a-449f-a011-0d642fd5423d · outbound

This paper cites Unlearnable algorithms for in-context learning.arXiv preprint arXiv:2402.00751, 2024.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Unlearnable algorithms for in-context learning.arXiv preprint arXiv:2402.00751, 2024

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.818528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c59558da-a620-4fc9-9172-f4a4bed27697 · outbound

This paper cites Rectified linear units improve restricted boltzmann machines.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Rectified linear units improve restricted boltzmann machines

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.822276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0c5cc9d-d11e-43e8-9cae-50a5712ac8b3 · outbound

This paper cites Token cleaning: Fine-grained data selection for llm supervised fine-tuning.arXiv preprint arXiv:2502.01968, 2025.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Token cleaning: Fine-grained data selection for llm supervised fine-tuning.arXiv preprint arXiv:2502.01968, 2025

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.825974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 804a9e64-4ad9-417d-98f7-199939e8049a · outbound

This paper cites Improving data efficiency via curating LLM-driven rating systems.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Improving data efficiency via curating LLM-driven rating systems

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.829338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71a06f07-7ff9-4264-8560-d6d2b901f7b9 · outbound

This paper cites Bleu: a method for automatic evaluation of machine translation.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Bleu: a method for automatic evaluation of machine translation

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.833907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c88d18ce-f1cc-49c2-801a-bc07ac169b67 · outbound

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

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection In-Context Unlearning: Language Models as Few Shot Unlearners

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.837453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c82ba4b4-e44b-45f8-8d58-748ce222b784 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Direct preference optimization: Your language model is secretly a reward model

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.841648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72e70db7-5fde-4790-89be-1d40495af6e2 · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.Journal of machine learning research, 21(140):1–67, 2020.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Exploring the limits of transfer learning with a unified text-to-text transformer.Journal of machine learning research, 21(140):1–67, 2020

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.845431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2299086-9103-4dbf-ab89-afa0f30a1519 · outbound

This paper cites SQuAD: 100,000+ Questions for Machine Comprehension of Text.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection SQuAD: 100,000+ Questions for Machine Comprehension of Text

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.849331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d6236bd-7d0f-423c-b430-b45740270c74 · outbound

This paper cites LUME: LLM Unlearning with Multitask Evaluations.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection LUME: LLM Unlearning with Multitask Evaluations

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.853165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e29911c-287c-4e37-acee-2f260c51e111 · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.857342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4ec0f6e-0d7b-4c16-8451-b0962d4350b5 · outbound

This paper cites Scholastic Incorporated, 2023.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Scholastic Incorporated, 2023

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.861092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae260f04-c9c9-4202-9fdd-81110a24b291 · outbound

This paper cites Winogrande: An adversarial winograd schema challenge at scale.Communications of the ACM, 64(9):99–106, 2021.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Winogrande: An adversarial winograd schema challenge at scale.Communications of the ACM, 64(9):99–106, 2021

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.864885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8c21e6a-28bb-44e3-9adc-64c137c5aa72 · outbound

This paper cites Detecting Pretraining Data from Large Language Models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Detecting Pretraining Data from Large Language Models

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.868297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dfbce3b-c3c3-498e-abc0-679dba0b83e5 · outbound

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

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.871983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b53763d-bd1c-4ad0-b732-df2112c71c6e · outbound

This paper cites Large language models encode clinical knowledge.Nature, 620(7972):172–180, 2023.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Large language models encode clinical knowledge.Nature, 620(7972):172–180, 2023

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.876291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2baaf251-8055-4499-b99b-c2a655b296fd · outbound

This paper cites Beyond Memorization: Violating Privacy Via Inference with Large Language Models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Beyond Memorization: Violating Privacy Via Inference with Large Language Models

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.880350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe7f63e8-b3a0-4db9-b65a-b3644cb1a661 · outbound

This paper cites Galactica: A Large Language Model for Science.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Galactica: A Large Language Model for Science

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.884163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e75d97f-394b-4e23-ad84-94fbe293e8a2 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Gemini: A Family of Highly Capable Multimodal Models

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.887676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71b8607b-f3dd-4c22-abe2-b083031b5d49 · outbound

This paper cites The falcon 3 family of open models, December 2024.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection The falcon 3 family of open models, December 2024

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.891622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52c73be3-98bb-4f4d-beab-8c61a52af5d4 · outbound

This paper cites Guardrail Baselines for Unlearning in LLMs.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Guardrail Baselines for Unlearning in LLMs

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.895079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 647484dd-bf91-40c5-9502-28218dee089b · outbound

This paper cites Memorization without overfitting: Analyzing the training dynamics of large language models.Advances in Neural Information Processing Systems, 35:38274–38290, 2022.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Memorization without overfitting: Analyzing the training dynamics of large language models.Advances in Neural Information Processing Systems, 35:38274–38290, 2022

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.899090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12906d9d-2c2b-4a14-819f-f363c71df942 · outbound

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

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.902583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5778b8d2-bf7a-4bdd-8830-f41a563f70c8 · outbound

This paper cites KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.906241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec87b60b-66dd-4b03-bec4-fade92c7afa3 · outbound

This paper cites LLM Unlearning via Loss Adjustment with Only Forget Data.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection LLM Unlearning via Loss Adjustment with Only Forget Data

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.910131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd25faeb-d8b9-4cb3-8ba8-ec5af3903cf0 · outbound

This paper cites Distributionally robust post-hoc classifiers under prior shifts.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Distributionally robust post-hoc classifiers under prior shifts

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.913972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d47862e-113f-4b1d-9df9-28d593fd60af · outbound

This paper cites Measuring and Reducing LLM Hallucination without Gold-Standard Answers.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Measuring and Reducing LLM Hallucination without Gold-Standard Answers

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.917798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78e11f5c-d982-4dab-a9ab-29e7344220b2 · outbound

This paper cites Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.922316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5641037-d00f-43b6-a2d5-7544d8b58ac4 · outbound

This paper cites Machine Unlearning for Traditional Models and Large Language Models: A Short Survey.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Machine Unlearning for Traditional Models and Large Language Models: A Short Survey

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.926816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f274635-e810-4eda-97bf-49f0ade0dbcf · outbound

This paper cites MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.931675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19048c04-94c3-432a-a530-6193a414e309 · outbound

This paper cites Qwen2.5 Technical Report.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Qwen2.5 Technical Report

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.935651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d6750f5-3e60-4840-b185-9e181fef34a4 · outbound

This paper cites Machine Unlearning of Pre-trained Large Language Models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Machine Unlearning of Pre-trained Large Language Models

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.939755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6c32854-0696-45a1-a519-675f6ed005b8 · outbound

This paper cites Large language model unlearning.Advances in Neural Information Processing Systems, 37:105425–105475, 2024.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Large language model unlearning.Advances in Neural Information Processing Systems, 37:105425–105475, 2024

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:39.943769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3ef7cb7-4634-4f32-b1c1-688cd0b14ca0 · outbound

This paper cites Enhanced membership inference attacks against machine learning models.

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection Enhanced membership inference attacks against machine learning models

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:21:41.076001Z

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.

Pith citing papers

Observation 288ca9e8-4228-4e6d-8f97-4209e5d4640f · inbound

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

SoK: Machine Unlearning for Large Language Models GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T04:58:53.560741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76661dab-7cfa-45be-9e30-edf81ba2859b · inbound

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

Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:46:17.073910Z

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 366e5cca-85ef-464b-9600-766316b61a7d · inbound

NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding cites this paper.

NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T05:36:25.927251Z

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 d50c33c0-e594-4a35-897b-5a94ad803b95 · 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 GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection

Reference 112

Resolution: verified exact; arxiv_id, observed 2026-05-19T21:52:48.232469Z

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 2ba229bb-95b0-4938-baca-89fde522a047 · inbound

Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning cites this paper.

Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:03:51.462591Z

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 1b8db8b2-702a-4227-96ea-b911df4b3608 · inbound

Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning cites this paper.

Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection

Reference 183

Resolution: unresolved; no resolver link, observed 2026-08-15T14:17:57.144501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.