Who's Harry Potter? Approximate Unlearning in LLMs | Paper Citation Record

Observation f0e0d19d-04b7-4eb4-afdc-1bc3182c33d1 · inbound

Detecting Pretraining Data from Large Language Models cites this paper.

Detecting Pretraining Data from Large Language Models Who's Harry Potter? Approximate Unlearning in LLMs

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:07:24.698484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 598f60e9-ed85-4b6f-947f-cb1993a91998 · inbound

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

TOFU: A Task of Fictitious Unlearning for LLMs Who's Harry Potter? Approximate Unlearning in LLMs

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-16T11:07:39.257550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7e5c0730-e726-4802-ba6d-12b0f4098f21 · inbound

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

Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:26:55.121809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 374ab85c-f1c6-475c-8dac-27ae063128ce · inbound

AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions cites this paper.

AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions Who's Harry Potter? Approximate Unlearning in LLMs

Reference 197

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:55:50.625879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2608956e-4e6b-4836-a99b-31cd34af3b56 · inbound

Improving LLM Unlearning Robustness via Random Perturbations cites this paper.

Improving LLM Unlearning Robustness via Random Perturbations Who's Harry Potter? Approximate Unlearning in LLMs

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:42:33.319702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fb8af10f-97a8-49c9-81e2-5892aa7d8e30 · inbound

Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating cites this paper.

Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating Who's Harry Potter? Approximate Unlearning in LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T20:04:49.989615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4da03d3-2819-4841-8be7-58c05f293e89 · inbound

Agents Are All You Need for LLM Unlearning cites this paper.

Agents Are All You Need for LLM Unlearning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T19:14:53.259874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b2f1e2e-7802-40da-ba21-c122e58bf5c1 · inbound

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

Position: Adversarial ML for LLMs Is Not Making Any Progress Who's Harry Potter? Approximate Unlearning in LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T12:47:21.658282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8c35643-e71d-4213-8334-eb6811ec4146 · inbound

Code Simulation as a Proxy for High-order Tasks in Large Language Models cites this paper.

Code Simulation as a Proxy for High-order Tasks in Large Language Models Who's Harry Potter? Approximate Unlearning in LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T04:32:42.198520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb44ab29-1486-44c8-b049-ea1d1b5aed00 · inbound

A Lightweight Method to Disrupt Memorized Sequences in LLM cites this paper.

A Lightweight Method to Disrupt Memorized Sequences in LLM Who's Harry Potter? Approximate Unlearning in LLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.341933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b418230-7637-46a3-8264-eefe9bda0124 · inbound

DUSK: Do Not Unlearn Shared Knowledge cites this paper.

DUSK: Do Not Unlearn Shared Knowledge Who's Harry Potter? Approximate Unlearning in LLMs

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:26:22.041584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 359706bb-e0d8-4104-90dd-4ab92dd09261 · inbound

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

Existing Large Language Model Unlearning Evaluations Are Inconclusive Who's Harry Potter? Approximate Unlearning in LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:05:54.154286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b1f6e7d-8644-4b44-8abc-634f46722183 · inbound

Targeted Forgetting of Image Subgroups in CLIP Models cites this paper.

Targeted Forgetting of Image Subgroups in CLIP Models Who's Harry Potter? Approximate Unlearning in LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T11:15:29.619462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfa38018-9df5-4b21-973f-22a7c793d74b · inbound

Certified Unlearning for Neural Networks cites this paper.

Certified Unlearning for Neural Networks Who's Harry Potter? Approximate Unlearning in LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T06:00:39.550593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2bc94c4-c38a-4dad-aac4-0c14327d6dfa · inbound

LLM Unlearning Should Be Form-Independent cites this paper.

LLM Unlearning Should Be Form-Independent Who's Harry Potter? Approximate Unlearning in LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:33:33.480384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d69c8966-0943-4b31-b2a0-1a927c408261 · inbound

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

SoK: Machine Unlearning for Large Language Models Who's Harry Potter? Approximate Unlearning in LLMs

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T04:58:50.652465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6224a955-ca34-442b-aeb5-51011391d676 · inbound

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

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods Who's Harry Potter? Approximate Unlearning in LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T04:37:06.784382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a873164-27e0-4932-9b91-e1a2168124e7 · inbound

Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models cites this paper.

Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models Who's Harry Potter? Approximate Unlearning in LLMs

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-07T04:16:59.023293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a625eacf-d782-4124-95f3-457d74ccc836 · inbound

SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation cites this paper.

SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation Who's Harry Potter? Approximate Unlearning in LLMs

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T00:46:10.029882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa0ba5a9-6e66-4982-a548-b54f0c95ec7c · inbound

The Space Complexity of Learning-Unlearning Algorithms cites this paper.

The Space Complexity of Learning-Unlearning Algorithms Who's Harry Potter? Approximate Unlearning in LLMs

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:46.902359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d34981c5-ff54-4594-bb03-e46b56fb9b1b · 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 Who's Harry Potter? Approximate Unlearning in LLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:01:32.595672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 295d9b49-6d0f-464a-a8b9-7a2a4f3e1cf2 · inbound

Revisiting the Past: Data Unlearning with Model State History cites this paper.

Revisiting the Past: Data Unlearning with Model State History Who's Harry Potter? Approximate Unlearning in LLMs

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-19T08:13:01.704958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6a9082b9-f821-46e3-8247-42da4155c540 · 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 Who's Harry Potter? Approximate Unlearning in LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T19:59:51.137003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12ccf385-c969-4337-b35c-c33e0a977a26 · 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 Who's Harry Potter? Approximate Unlearning in LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:33.578374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbd3030e-c2fd-4d2e-8fd3-060ff1a1f8e4 · inbound

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models cites this paper.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Who's Harry Potter? Approximate Unlearning in LLMs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:22.691578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 924c70f7-15f7-4cb5-b7c1-90ba9296654a · inbound

iShumei-Chinchunmei at SemEval-2025 Task 4: A balanced forgetting and retention multi-task framework using effective unlearning loss cites this paper.

iShumei-Chinchunmei at SemEval-2025 Task 4: A balanced forgetting and retention multi-task framework using effective unlearning loss Who's Harry Potter? Approximate Unlearning in LLMs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T15:22:15.992489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b30c81e-2f10-4bc0-9448-4182fdb85951 · 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 Who's Harry Potter? Approximate Unlearning in LLMs

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T13:54:39.587728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be23f11c-aa99-4441-881a-a78550e90ab1 · inbound

Towards Integrated Alignment cites this paper.

Towards Integrated Alignment Who's Harry Potter? Approximate Unlearning in LLMs

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-05T22:56:28.183707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7056a38-ea2d-44f9-9b56-dec1254c3b40 · inbound

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

Module-Aware Parameter-Efficient Machine Unlearning on Transformers Who's Harry Potter? Approximate Unlearning in LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T17:06:08.904149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fb34b7f-5f79-4056-945a-5dabe56ed02f · inbound

LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems cites this paper.

LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems Who's Harry Potter? Approximate Unlearning in LLMs

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-04T17:46:17.162498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b93afa22-19dd-4a85-83fb-87542c2f3314 · inbound

OFMU: Optimization-Driven Framework for Machine Unlearning cites this paper.

OFMU: Optimization-Driven Framework for Machine Unlearning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-18T13:06:23.493363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bede1493-016e-437d-a4da-f852d5d58d62 · inbound

The Realignment Problem: When Right becomes Wrong in LLMs cites this paper.

The Realignment Problem: When Right becomes Wrong in LLMs Who's Harry Potter? Approximate Unlearning in LLMs

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-18T01:30:35.768487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bb69cc0c-8a5b-4536-9faa-636ec616d737 · inbound

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

RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories Who's Harry Potter? Approximate Unlearning in LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T18:41:34.006399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db175ba0-48ff-4dd8-924c-8b5e71f7d290 · inbound

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

A Mechanistic Perspective and Circuit-Guided Difficulty Metric for Unlearning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T10:37:00.366212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd55a782-bc3a-4c2b-8c64-b16af2412c3a · inbound

Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance cites this paper.

Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance Who's Harry Potter? Approximate Unlearning in LLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T01:20:06.622090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2033d400-ff81-4582-b8ab-16cdc8fee09a · inbound

CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization cites this paper.

CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization Who's Harry Potter? Approximate Unlearning in LLMs

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-10T08:53:04.763256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6bcac1bf-07e5-4958-b0c9-d2200f46efff · inbound

Position: No Retroactive Cure for Infringement during Training cites this paper.

Position: No Retroactive Cure for Infringement during Training Who's Harry Potter? Approximate Unlearning in LLMs

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-10T09:38:42.874431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4d970d56-ddc3-4190-94b9-48dc3d79bba6 · inbound

Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression cites this paper.

Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression Who's Harry Potter? Approximate Unlearning in LLMs

Reference 106

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:21:05.113947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9cb5a84a-7a90-4752-bafe-e1af968aa37d · inbound

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

Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies Who's Harry Potter? Approximate Unlearning in LLMs

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-09T22:34:07.380280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 90a83093-550e-4c82-8652-47cb32f3a399 · inbound

Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning cites this paper.

Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:36:06.707907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 43fe5645-feb8-46cb-a91b-707ed4be28e8 · inbound

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set cites this paper.

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set Who's Harry Potter? Approximate Unlearning in LLMs

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:11:08.470197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b5f63159-d29d-499f-a391-912ca1e277f5 · inbound

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set cites this paper.

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set Who's Harry Potter? Approximate Unlearning in LLMs

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-07-01T07:35:28.958459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 39144b72-90b9-4315-9eeb-bb93cdc95222 · 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 Who's Harry Potter? Approximate Unlearning in LLMs

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-09T05:55:30.179097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 888d02ba-f112-467b-8900-c563c7067f2e · inbound

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

DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-09T06:10:41.756539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9d9b4a98-2b6e-4fbf-9bfc-d5c15474c31f · inbound

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

DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T01:50:51.160115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e8461eee-7e29-484c-b0db-02dfa0521aef · inbound

Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models cites this paper.

Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models Who's Harry Potter? Approximate Unlearning in LLMs

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-15T01:43:27.397693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6e7d7b20-99f7-43d6-ad52-f23072e62aa4 · inbound

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models cites this paper.

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models Who's Harry Potter? Approximate Unlearning in LLMs

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T16:28:38.842438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 02d186bb-c04e-4963-9256-f552bf212358 · inbound

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models cites this paper.

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models Who's Harry Potter? Approximate Unlearning in LLMs

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T08:09:51.681184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0c415803-7923-4b94-a548-98f961453dc2 · inbound

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models cites this paper.

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models Who's Harry Potter? Approximate Unlearning in LLMs

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T19:35:01.467712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cf74c0b3-61c9-47c8-ac99-222eb2845735 · 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 Who's Harry Potter? Approximate Unlearning in LLMs

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:13:21.274913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6b055248-340c-4fcb-9fc3-fd29f6cbdcdc · inbound

Calibration vs Decision Making: Revisiting the Reliability Paradox in Unlearned Language Models cites this paper.

Calibration vs Decision Making: Revisiting the Reliability Paradox in Unlearned Language Models Who's Harry Potter? Approximate Unlearning in LLMs

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-21T04:49:35.730051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fd8d0a93-e4fd-4004-9a5c-f6daa31e6a89 · inbound

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

Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications Who's Harry Potter? Approximate Unlearning in LLMs

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-06-30T17:24:57.265788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d7da06b5-ec16-4f05-9bf6-28e667a5f05c · 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 Who's Harry Potter? Approximate Unlearning in LLMs

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:03:51.484661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2716d7a5-d921-4dec-a671-02c0b7b1904e · inbound

How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning cites this paper.

How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-01T22:26:17.359535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 62d44177-86dc-459f-b1fe-353bff5cadfe · inbound

AI as a Tool for Simulation-Based Experiments in Literary Studies cites this paper.

AI as a Tool for Simulation-Based Experiments in Literary Studies Who's Harry Potter? Approximate Unlearning in LLMs

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-06-28T15:02:19.036051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 36c6f97f-abf5-4eb5-ad1f-a926ca68412f · inbound

Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior cites this paper.

Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior Who's Harry Potter? Approximate Unlearning in LLMs

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-07-01T22:36:16.665986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5b6875ad-dbeb-432f-af2a-5c5681155ea2 · inbound

Fast Unlearning at Scale via Margin Self-Correction cites this paper.

Fast Unlearning at Scale via Margin Self-Correction Who's Harry Potter? Approximate Unlearning in LLMs

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-01T22:26:18.070385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6df2b21d-8a76-48c6-9bf7-7013792bf942 · inbound

Exact Unlearning in Reinforcement Learning cites this paper.

Exact Unlearning in Reinforcement Learning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:27.366507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4e382f14-a269-4568-8673-fc03572323e6 · inbound

REMEDI: A Benchmark for Retention and Unlearning Evaluation in Multi-label Clinical Disease Inference cites this paper.

REMEDI: A Benchmark for Retention and Unlearning Evaluation in Multi-label Clinical Disease Inference Who's Harry Potter? Approximate Unlearning in LLMs

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T16:57:09.461793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f4cb852a-c8ba-4ce6-9b9f-894ba93721a9 · inbound

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

TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation Who's Harry Potter? Approximate Unlearning in LLMs

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-02T20:07:21.173959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2c5520c9-7139-4962-9efe-799dbaba3d89 · inbound

Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning cites this paper.

Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-03T04:47:38.799656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7496b0aa-fd80-438e-9114-bb740ce6c235 · inbound

TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models cites this paper.

TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models Who's Harry Potter? Approximate Unlearning in LLMs

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-03T13:38:19.374326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3d3870ac-3a10-4d94-89e8-9c91a124e125 · inbound

Revocable Learned State via Process Sidecars cites this paper.

Revocable Learned State via Process Sidecars Who's Harry Potter? Approximate Unlearning in LLMs

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-01T06:45:29.316717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bcd8d6ae-8c0a-43a6-b326-947a2167cead · inbound

LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning cites this paper.

LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-07-03T14:18:22.521033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 74a66932-9a27-4741-8e65-e78d5a78ad27 · inbound

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

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem Who's Harry Potter? Approximate Unlearning in LLMs

Reference 7

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 87d12ed4-e1af-48a9-8b12-6f024ce47435 · inbound

Targeted Recovery of Weight-Space Mechanisms From Neural Networks cites this paper.

Targeted Recovery of Weight-Space Mechanisms From Neural Networks Who's Harry Potter? Approximate Unlearning in LLMs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T10:39:49.185997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 066efc56-e8c6-4a4a-8614-7b0594c4c869 · inbound

Targeted Recovery of Weight-Space Mechanisms From Neural Networks cites this paper.

Targeted Recovery of Weight-Space Mechanisms From Neural Networks Who's Harry Potter? Approximate Unlearning in LLMs

Reference 157

Resolution: unresolved; no resolver link, observed 2026-08-02T10:40:01.433208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56ff1ac6-2299-4509-a424-44471d4f1014 · inbound

Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning cites this paper.

Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T14:53:52.447720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1f25f05-704a-4deb-bbdf-2d74ab36da30 · inbound

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

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Who's Harry Potter? Approximate Unlearning in LLMs

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.493346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ac17632-07dd-4771-b3b8-d4e9eff3a476 · inbound

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

Understanding Machine Unlearning Through the Lens of Mode Connectivity Who's Harry Potter? Approximate Unlearning in LLMs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-31T23:27:25.873572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35e6c157-37b6-4ab3-8266-806b4bcc503b · inbound

Metis: Memory Foundation Model cites this paper.

Metis: Memory Foundation Model Who's Harry Potter? Approximate Unlearning in LLMs

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-30T21:56:17.834759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e283817d-3605-4fda-b707-af585bbf96ac · inbound

Metis: Memory Foundation Model cites this paper.

Metis: Memory Foundation Model Who's Harry Potter? Approximate Unlearning in LLMs

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-05T04:28:11.241402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b499c2a7-8cd3-48bd-9a37-29128534df76 · 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 Who's Harry Potter? Approximate Unlearning in LLMs

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T00:35:49.442437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 402f4099-6f57-4e93-b08d-76d064c20f88 · inbound

Beyond Binary Rewards: A Comparative Study of Reward Design for Reinforcement Unlearning cites this paper.

Beyond Binary Rewards: A Comparative Study of Reward Design for Reinforcement Unlearning Who's Harry Potter? Approximate Unlearning in LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-31T21:55:10.827361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78d48a70-6b9f-4d26-88e7-7aff1dddd13c · inbound

Exploring and Bridging Knowledge Holes in Unlearned Multimodal Large Language Models cites this paper.

Exploring and Bridging Knowledge Holes in Unlearned Multimodal Large Language Models Who's Harry Potter? Approximate Unlearning in LLMs

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T19:44:45.218541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c39feb90-8c4f-45ab-8cd7-73fcf0912036 · 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 Who's Harry Potter? Approximate Unlearning in LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T18:54:46.408366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers