Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning | Paper Citation Record

Observation 4b70818b-d1f3-43d5-9f4e-8850374580b1 · outbound

This paper cites In: Proceedingsofthe34thInternationalConferenceonNeuralInformationProcessing Systems.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Proceedingsofthe34thInternationalConferenceonNeuralInformationProcessing Systems

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:09.266821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 22b0066b-8c04-4725-8cd1-aa33e667b329 · outbound

This paper cites In: The Eleventh International Con- ference on Learning Representations (2023),https://openreview.net/forum?id= TatRHT_1cK.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: The Eleventh International Con- ference on Learning Representations (2023),https://openreview.net/forum?id= TatRHT_1cK

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:09.043248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ab414a25-40f3-402c-9c7d-434356ec3e3a · outbound

This paper cites In: 30th USENIX Security Symposium (USENIX Security 21).

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: 30th USENIX Security Symposium (USENIX Security 21)

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:08.854588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 131b2afa-910c-4d5a-91d6-a2b3a898d232 · outbound

This paper cites In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:08.635059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 621bbbbb-5146-4073-a35b-19ae64d37a84 · outbound

This paper cites In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T

Reference 5

Resolution: verified exact; doi, observed 2026-08-05T13:55:02.677414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 51b163bb-74e6-4ed5-861a-442d2c71d529 · outbound

This paper cites ARC Prize 2024: Technical Report.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning ARC Prize 2024: Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:59.252066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5135c40-1b1e-4f54-87fc-490f75b1e728 · outbound

This paper cites com/locuslab/open-unlearning (2025), accessed: February 27, 2025.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning com/locuslab/open-unlearning (2025), accessed: February 27, 2025

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:08.445441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation de439379-7619-4929-bc7c-238fcde5f070 · outbound

This paper cites an unresolved cited work.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-05T13:55:08.217686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e27f72d9-9445-44b8-90d6-5a1cfe8fea44 · outbound

This paper cites In: 2020 IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition (CVPR).

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: 2020 IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition (CVPR)

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:59.655496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe38c742-7228-4b99-9c73-f9362e5cf49b · outbound

This paper cites The Llama 3 Herd of Models.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:59.787082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf2b9781-5476-4422-8caf-3a2b2e8f5574 · outbound

This paper cites In: International Con- ference on Learning Representations (2022),https://openreview.net/forum?id= nZeVKeeFYf9.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: International Con- ference on Learning Representations (2022),https://openreview.net/forum?id= nZeVKeeFYf9

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T13:54:59.912190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f63b326-2d95-484e-99ae-a55a1010e3ea · outbound

This paper cites In: Rogers, A., Boyd-Graber, J., Okazaki, N.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Rogers, A., Boyd-Graber, J., Okazaki, N

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T13:55:00.010038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 284d5597-36ec-4214-a2f3-debbb9780c91 · outbound

This paper cites In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024), https://openreview.net/forum?id=tYdR1lTWqh.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024), https://openreview.net/forum?id=tYdR1lTWqh

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:08.000943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0be7bd39-c607-4f76-ade3-2487d96fe3f5 · outbound

This paper cites In: The Thirty-eight Conference on Neural Information Processing Sys- tems Datasets and Benchmarks Track (2024),https://openreview.net/forum? id=wOmtZ5FgMH Standard vs.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: The Thirty-eight Conference on Neural Information Processing Sys- tems Datasets and Benchmarks Track (2024),https://openreview.net/forum? id=wOmtZ5FgMH Standard vs

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:07.780657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7d1a802b-2558-4ba8-9f2b-54824be24f95 · outbound

This paper cites In: Sec- ond Conference on Language Modeling (2025),https://openreview.net/forum? id=Kd97lfFfTu.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Sec- ond Conference on Language Modeling (2025),https://openreview.net/forum? id=Kd97lfFfTu

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:07.561223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c250bd80-6131-4436-854d-cc588e855097 · outbound

This paper cites In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Hu- man Language Technologies.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Hu- man Language Technologies

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T13:55:00.587663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d1b9631-49fc-4ebf-9810-2574234581d1 · outbound

This paper cites In: Proceedings of the 41st Inter- national Conference on Machine Learning.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Proceedings of the 41st Inter- national Conference on Machine Learning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:07.229102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d0477187-4615-4609-bac0-18b557484995 · outbound

This paper cites In: Text Summarization Branches Out.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Text Summarization Branches Out

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:06.980212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 86a5d8cc-41a5-4e0b-a85a-53e750d85a51 · outbound

This paper cites Continual Learning and Private Unlearning.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning Continual Learning and Private Unlearning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T13:55:00.880030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad40f035-8ad0-47a2-8129-7255eb3644d4 · outbound

This paper cites Nature Machine Intelligence 7, 181–194 (2025).

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning Nature Machine Intelligence 7, 181–194 (2025)

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T13:55:00.958060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73116815-f353-46c0-82bb-0bd73b3ea877 · outbound

This paper cites In: Proceed- ings of the 2024 Conference on Empirical Methods in Natural Language Process- ing.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Proceed- ings of the 2024 Conference on Empirical Methods in Natural Language Process- ing

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T13:55:01.056132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de6c79cf-c074-4347-9378-40d1ade15427 · outbound

This paper cites In: First Conference on Language Modeling (2024), https://openreview.net/forum?id=B41hNBoWLo.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: First Conference on Language Modeling (2024), https://openreview.net/forum?id=B41hNBoWLo

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:06.765088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f557a0ca-1c10-4d44-b41f-fe226e543617 · outbound

This paper cites In: Proceedings of the 31st International Con- ference on Computational Linguistics.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Proceedings of the 31st International Con- ference on Computational Linguistics

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:06.490222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c75212f0-ac45-4382-a88d-c26b4a7db34f · outbound

This paper cites Transactions on Machine Learning Research (2025),https://openreview.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning Transactions on Machine Learning Research (2025),https://openreview

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:06.233087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 09812346-418c-47dc-81b0-e0551807476a · outbound

This paper cites In: Rosen- thal, S., Rosá, A., Ghosh, D., Zampieri, M.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Rosen- thal, S., Rosá, A., Ghosh, D., Zampieri, M

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:05.925942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 627142d9-09d7-4f34-a78b-efc15e335f0b · outbound

This paper cites How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T13:55:01.349922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca0132d4-263f-4bb1-a760-72eabfa543a1 · outbound

This paper cites In: Pro- ceedings of the 37th International Conference on Neural Information Processing Systems.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Pro- ceedings of the 37th International Conference on Neural Information Processing Systems

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:05.671756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 518c836e-ffd4-4ed8-88cb-798bfcea5c4e · outbound

This paper cites In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:05.399869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a0b5d9f8-5be6-4381-9cef-ed7809cee454 · outbound

This paper cites In: The Twelfth International Conference on Learning Representations (2024),https://openreview.net/forum? id=kmn0BhQk7p.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: The Twelfth International Conference on Learning Representations (2024),https://openreview.net/forum? id=kmn0BhQk7p

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:05.119161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7c6d5820-0f5c-4050-a7ac-296383202121 · outbound

This paper cites Position: LLM Unlearning Benchmarks are Weak Measures of Progress.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning Position: LLM Unlearning Benchmarks are Weak Measures of Progress

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T13:55:01.621509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d6c706c-0883-4c76-bb39-0b7c9eac5353 · outbound

This paper cites In: Oh,A.H.,Agarwal,A.,Belgrave,D.,Cho,K.(eds.)AdvancesinNeuralInformation Processing Systems (2022),https://openreview.net/forum?id=u3vEuRr08MT.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Oh,A.H.,Agarwal,A.,Belgrave,D.,Cho,K.(eds.)AdvancesinNeuralInformation Processing Systems (2022),https://openreview.net/forum?id=u3vEuRr08MT

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:04.885774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9db2e64c-55de-4bd5-aa8e-c6ad80c2c574 · outbound

This paper cites In: Proceedings of the 31st International Conference on Neural Information Processing Systems.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: Proceedings of the 31st International Conference on Neural Information Processing Systems

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T13:55:01.824289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fab1e539-6023-452d-87ef-efdbec717909 · outbound

This paper cites In: The Thirteenth International Conference on Learning Representations (2025),https: //openreview.net/forum?id=huo8MqVH6t.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: The Thirteenth International Conference on Learning Representations (2025),https: //openreview.net/forum?id=huo8MqVH6t

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:04.653025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3c90f828-096b-480c-bf77-958bc06d5451 · outbound

This paper cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T13:55:01.947238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 912451e0-fadd-4070-9ae0-8f91e5d00818 · outbound

This paper cites In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024),https:// openreview.net/forum?id=8Dy42ThoNe.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024),https:// openreview.net/forum?id=8Dy42ThoNe

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:04.411831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b8ac810d-2f42-4efe-b558-b0679b95ce67 · outbound

This paper cites In: The Thirteenth International Con- ference on Learning Representations (2025),https://openreview.net/forum?id= Q1MHvGmhyT.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: The Thirteenth International Con- ference on Learning Representations (2025),https://openreview.net/forum?id= Q1MHvGmhyT

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:04.101957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7aa6a031-3eb6-4572-85de-c18b43a7674c · outbound

This paper cites (eds.) Proceedings of the 57th Annual Meeting of the Association for Com- putational Linguistics.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning (eds.) Proceedings of the 57th Annual Meeting of the Association for Com- putational Linguistics

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T13:55:02.190516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5a48b5f-af62-40c5-a8e1-db8ce73780a1 · outbound

This paper cites In: First Conference on Language Modeling (2024), https://openreview.net/forum?id=MXLBXjQkmb Standard vs.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning In: First Conference on Language Modeling (2024), https://openreview.net/forum?id=MXLBXjQkmb Standard vs

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:03.927818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cc1285c1-7f53-4145-bf2b-a8933a4e0402 · outbound

This paper cites name": name of the person,.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning name": name of the person,

Reference 39

Resolution: metadata mismatch; raw_fallback, observed 2026-08-05T13:55:03.196991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 45980714-2cc5-4cec-9ef7-467c5cad5abb · outbound

This paper cites ROUGE-L provides the longest sequence overlap and the verbatim memory of the Unlearned Model(M ; θ∗).

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning ROUGE-L provides the longest sequence overlap and the verbatim memory of the Unlearned Model(M ; θ∗)

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:55:03.653398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 51556dbf-1532-4096-9513-88fa96eff6c8 · outbound

This paper cites 5966–5982.

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning 5966–5982

Reference 2025

Resolution: verified exact; doi, observed 2026-08-05T13:55:02.885319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers