A Lightweight Method to Disrupt Memorized Sequences in LLM | Paper Citation Record

Observation fc06a381-c6de-4988-94eb-a172d01e7931 · outbound

This paper cites Copyright-Protected Language Generation via Adaptive Model Fusion.

A Lightweight Method to Disrupt Memorized Sequences in LLM Copyright-Protected Language Generation via Adaptive Model Fusion

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-08T20:08:57.953888Z

Source-reported events for the cited work

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

Observation 6fbe8091-c76a-4f29-993d-7f213dd0d3e1 · outbound

This paper cites Deep learning with differential privacy.

A Lightweight Method to Disrupt Memorized Sequences in LLM Deep learning with differential privacy

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.253008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8959d6a-46b3-49eb-b5cb-c0a748f279a5 · outbound

This paper cites GPT-4 Technical Report.

A Lightweight Method to Disrupt Memorized Sequences in LLM GPT-4 Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.256985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f656a0f-a84b-413c-b257-814d9beb584a · outbound

This paper cites SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model.

A Lightweight Method to Disrupt Memorized Sequences in LLM SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.261674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dd82cc8-3118-4921-b6f6-d25a72487b88 · outbound

This paper cites Physics of language models: Part 3.3, knowledge capacity scaling laws.

A Lightweight Method to Disrupt Memorized Sequences in LLM Physics of language models: Part 3.3, knowledge capacity scaling laws

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.222638Z

Source-reported events for the cited work

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

Observation 807bf33c-57d7-452b-9f79-7ea34005f6ae · outbound

This paper cites Large-Scale Differentially Private BERT.

A Lightweight Method to Disrupt Memorized Sequences in LLM Large-Scale Differentially Private BERT

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.270395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89d0b8c9-37f5-4fad-afc5-bfc94d30165e · outbound

This paper cites Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization.

A Lightweight Method to Disrupt Memorized Sequences in LLM Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.275663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 349d2339-b466-4c0b-aaee-38d5a8e5f8ca · outbound

This paper cites Mirostat: A Neural Text Decoding Algorithm that Directly Controls Perplexity.

A Lightweight Method to Disrupt Memorized Sequences in LLM Mirostat: A Neural Text Decoding Algorithm that Directly Controls Perplexity

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.279687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 195b94fb-221a-4670-b05a-4515bac6a188 · outbound

This paper cites Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling.

A Lightweight Method to Disrupt Memorized Sequences in LLM Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.283516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa61a99b-9f3a-420e-961d-f6a993ed8ae5 · outbound

This paper cites Emergent and predictable memorization in large language models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Emergent and predictable memorization in large language models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.287563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34aadf66-5f4e-41c8-bac9-13250cbdf6f1 · outbound

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

A Lightweight Method to Disrupt Memorized Sequences in LLM Piqa: Reasoning about physical commonsense in natural language

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.291266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47d69e1c-7096-48a4-ad8c-3cb3c15ea156 · outbound

This paper cites Wikipedia, the free encyclopedia.

A Lightweight Method to Disrupt Memorized Sequences in LLM Wikipedia, the free encyclopedia

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.200038Z

Source-reported events for the cited work

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

Observation fa722a2d-d573-47f2-87ee-29a7f5ee5fb1 · outbound

This paper cites Targeted memorized‐data unlearning for large language models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Targeted memorized‐data unlearning for large language models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.189060Z

Source-reported events for the cited work

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

Observation eb2ef0b0-5d0f-4317-a106-b4164bd961e0 · outbound

This paper cites Extracting training data from large language models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Extracting training data from large language models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.301920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fe3a03b-f428-4690-93e2-1dce58bb4ce5 · outbound

This paper cites Quantifying Memorization Across Neural Language Models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Quantifying Memorization Across Neural Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.305404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09fe5233-3b88-484a-a2e0-750c08b3e6a0 · outbound

This paper cites Do localization methods actually localize memorized data in llms? a tale of two benchmarks.

A Lightweight Method to Disrupt Memorized Sequences in LLM Do localization methods actually localize memorized data in llms? a tale of two benchmarks

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.172298Z

Source-reported events for the cited work

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

Observation a3efbc0b-3346-43bc-9782-15ed867e906e · outbound

This paper cites Neural surgery for memorisation: Locating and removing verbatim recall neurons.

A Lightweight Method to Disrupt Memorized Sequences in LLM Neural surgery for memorisation: Locating and removing verbatim recall neurons

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.161104Z

Source-reported events for the cited work

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

Observation 65a35925-5fc3-42b2-a5d6-d2abfdab0984 · outbound

This paper cites The Geometry of Constant Function Market Makers.

A Lightweight Method to Disrupt Memorized Sequences in LLM The Geometry of Constant Function Market Makers

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.318096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3142da95-84b7-45da-9503-ac79ab796a6d · outbound

This paper cites ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data.

A Lightweight Method to Disrupt Memorized Sequences in LLM ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.322125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b70624b-e620-4e46-8066-e6a7ed0db8c3 · outbound

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

A Lightweight Method to Disrupt Memorized Sequences in LLM BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.325819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eb2ecef-7cf6-4752-92a2-f12810a78d74 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

A Lightweight Method to Disrupt Memorized Sequences in LLM Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.330593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb1b3609-a6cc-40e8-bfae-d36ae43bf38b · outbound

This paper cites The corpus of contemporary american english as the first reliable monitor corpus of english.

A Lightweight Method to Disrupt Memorized Sequences in LLM The corpus of contemporary american english as the first reliable monitor corpus of english

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.149771Z

Source-reported events for the cited work

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

Observation 00fc16e0-f1da-4091-8a71-99ac84cfb233 · outbound

This paper cites The Llama 3 Herd of Models.

A Lightweight Method to Disrupt Memorized Sequences in LLM The Llama 3 Herd of Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.338218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

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

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 acac0fc0-d61c-4747-a5ea-b52e3da919a6 · outbound

This paper cites Can Copyright be Reduced to Privacy?.

A Lightweight Method to Disrupt Memorized Sequences in LLM Can Copyright be Reduced to Privacy?

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-08T20:08:57.814487Z

Source-reported events for the cited work

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

Observation 5d7397fc-d826-4601-b4e7-d9985e5fbe0e · outbound

This paper cites Hierarchical Neural Story Generation.

A Lightweight Method to Disrupt Memorized Sequences in LLM Hierarchical Neural Story Generation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.350286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5b20004-ccb1-4fc0-8109-bf49ba8a772f · outbound

This paper cites Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit.

A Lightweight Method to Disrupt Memorized Sequences in LLM Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.353850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25398975-271e-46e0-912b-3f11b98d8bb5 · outbound

This paper cites The times sues openai and microsoft over ai use of copyrighted work.

A Lightweight Method to Disrupt Memorized Sequences in LLM The times sues openai and microsoft over ai use of copyrighted work

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.139277Z

Source-reported events for the cited work

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

Observation daadf5f6-4e4c-40d4-87f5-1f1f1d074a43 · outbound

This paper cites Leetcode problem dataset, 2021.

A Lightweight Method to Disrupt Memorized Sequences in LLM Leetcode problem dataset, 2021

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.128737Z

Source-reported events for the cited work

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

Observation 3d26e1d3-e9c8-4333-b763-5ee1d05470bd · outbound

This paper cites Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs.

A Lightweight Method to Disrupt Memorized Sequences in LLM Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.365034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b5f86ce-1c4d-4fd1-aef5-8d253e9d7ad4 · outbound

This paper cites SoK: Memorization in General-Purpose Large Language Models.

A Lightweight Method to Disrupt Memorized Sequences in LLM SoK: Memorization in General-Purpose Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.369870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23a1376e-4b33-4bb5-86f9-22277cf77a6f · outbound

This paper cites LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models.

A Lightweight Method to Disrupt Memorized Sequences in LLM LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.373671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84ff37c5-46d0-4732-a194-298cbc6d3c49 · outbound

This paper cites Demystifying Verbatim Memorization in Large Language Models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Demystifying Verbatim Memorization in Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.377140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bc12b95-f8ac-44cc-97a5-a9bb4ea893db · outbound

This paper cites Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy.

A Lightweight Method to Disrupt Memorized Sequences in LLM Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.381019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebc86268-dd95-4bda-9aab-b04964ea159d · outbound

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

A Lightweight Method to Disrupt Memorized Sequences in LLM Knowledge Unlearning for Mitigating Privacy Risks in Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.384769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 170397e8-c715-4f70-ba57-81fbb3235fc2 · outbound

This paper cites Deduplicating training data mitigates privacy risks in language models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Deduplicating training data mitigates privacy risks in language models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.117084Z

Source-reported events for the cited work

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

Observation 2f45330f-b883-462a-8846-a0c872513e62 · outbound

This paper cites Copyright Violations and Large Language Models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Copyright Violations and Large Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.393267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 665d368c-3858-4c8c-8e26-762581105b80 · outbound

This paper cites Big-little decoder: Faster language generation with an auxiliary model.

A Lightweight Method to Disrupt Memorized Sequences in LLM Big-little decoder: Faster language generation with an auxiliary model

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.105232Z

Source-reported events for the cited work

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

Observation df7f59d6-8712-41a5-a7c4-2f16c88bcb9d · outbound

This paper cites Fast inference from transformers via speculative decoding.

A Lightweight Method to Disrupt Memorized Sequences in LLM Fast inference from transformers via speculative decoding

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.093558Z

Source-reported events for the cited work

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

Observation f90f4c37-637b-4061-80f9-90a6943510d2 · outbound

This paper cites Contrastive decoding: Open-ended text generation as conditional density estimation.

A Lightweight Method to Disrupt Memorized Sequences in LLM Contrastive decoding: Open-ended text generation as conditional density estimation

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.081975Z

Source-reported events for the cited work

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

Observation 7d5c5bf9-f9db-43e4-9c49-9eaaaac4dd13 · outbound

This paper cites DeepSeek-V3 Technical Report.

A Lightweight Method to Disrupt Memorized Sequences in LLM DeepSeek-V3 Technical Report

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.409176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5bc4549-1fc4-48d5-9240-7018971984d9 · outbound

This paper cites NLTK: The Natural Language Toolkit.

A Lightweight Method to Disrupt Memorized Sequences in LLM NLTK: The Natural Language Toolkit

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.413302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff8e80df-79af-449c-9340-e2601a2b0dd3 · outbound

This paper cites Can Neural Network Memorization Be Localized?.

A Lightweight Method to Disrupt Memorized Sequences in LLM Can Neural Network Memorization Be Localized?

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.417863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 453f33d7-069c-401b-921b-9550b708f79e · outbound

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

A Lightweight Method to Disrupt Memorized Sequences in LLM Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.422630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4be2acd5-1f7b-41da-b179-f7aca784429b · outbound

This paper cites Memorization in NLP Fine-tuning Methods.

A Lightweight Method to Disrupt Memorized Sequences in LLM Memorization in NLP Fine-tuning Methods

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.426733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f427f2f-7094-4895-af91-af8225b2175a · outbound

This paper cites Scalable Extraction of Training Data from (Production) Language Models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Scalable Extraction of Training Data from (Production) Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.430369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ed45db8-3804-4be8-be55-6e093a165be9 · outbound

This paper cites Scalable extraction of training data from aligned, production language models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Scalable extraction of training data from aligned, production language models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.070573Z

Source-reported events for the cited work

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

Observation 47932ff0-966d-4c0d-815d-68511430a0aa · outbound

This paper cites Generative ai and copyright issues globally: Ani media v openai.

A Lightweight Method to Disrupt Memorized Sequences in LLM Generative ai and copyright issues globally: Ani media v openai

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.059329Z

Source-reported events for the cited work

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

Observation 70fa3916-a3f1-40c6-a62e-f33dbdbb5e3c · outbound

This paper cites The Fair Language Model Paradox.

A Lightweight Method to Disrupt Memorized Sequences in LLM The Fair Language Model Paradox

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.442425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edd3352d-1ed9-4f08-a78f-fb7c65921c47 · outbound

This paper cites Extracting Training Data from Document-Based VQA Models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Extracting Training Data from Document-Based VQA Models

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-08-08T20:08:57.650604Z

Source-reported events for the cited work

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

Observation a6c2f15d-1476-443a-90d6-5cd8eb1b4817 · outbound

This paper cites Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.451004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f079b7cc-6af9-4de8-bab4-67ab6fef6fd7 · outbound

This paper cites Winogrande: An adversarial winograd schema challenge at scale.

A Lightweight Method to Disrupt Memorized Sequences in LLM Winogrande: An adversarial winograd schema challenge at scale

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.454704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9c2bfa4-f079-4939-8372-0a2d0c15cf8d · outbound

This paper cites Mitigating Memorization In Language Models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Mitigating Memorization In Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.457970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b8bbf0f-0763-46cd-afca-7141ce5e7945 · outbound

This paper cites Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter.

A Lightweight Method to Disrupt Memorized Sequences in LLM Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.041547Z

Source-reported events for the cited work

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

Observation 63e7a741-a1e4-444b-8c21-1ff00b81d8fe · outbound

This paper cites SocialIQA: Commonsense Reasoning about Social Interactions.

A Lightweight Method to Disrupt Memorized Sequences in LLM SocialIQA: Commonsense Reasoning about Social Interactions

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.465476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 565692a6-1b0d-4ee9-bd2d-923e9b528af8 · outbound

This paper cites Rethinking LLM Memorization through the Lens of Adversarial Compression.

A Lightweight Method to Disrupt Memorized Sequences in LLM Rethinking LLM Memorization through the Lens of Adversarial Compression

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.470379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8feae682-7ffa-4ad0-8276-0a9d528e4b60 · outbound

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

A Lightweight Method to Disrupt Memorized Sequences in LLM UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.474018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 623241d4-a7c2-4651-af4e-a0236dcfee9f · outbound

This paper cites Slimpajama: A 627b token cleaned and deduplicated version of redpajama, 2023.

A Lightweight Method to Disrupt Memorized Sequences in LLM Slimpajama: A 627b token cleaned and deduplicated version of redpajama, 2023

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.477897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15894f9f-4382-49ce-8512-1eb64c032142 · outbound

This paper cites Blockwise parallel decoding for deep autoregressive models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Blockwise parallel decoding for deep autoregressive models

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.022757Z

Source-reported events for the cited work

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

Observation 5c292de2-8bb3-43b4-a04f-2b1cca06b852 · outbound

This paper cites Activation steering: Mitigating verbatim memorisation at inference time.

A Lightweight Method to Disrupt Memorized Sequences in LLM Activation steering: Mitigating verbatim memorisation at inference time

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:58.010704Z

Source-reported events for the cited work

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

Observation f4d851db-b509-484f-bc65-8f4584fcbddc · outbound

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

A Lightweight Method to Disrupt Memorized Sequences in LLM Gemini: A Family of Highly Capable Multimodal Models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.488782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07436a8c-e043-4a41-8d69-b03ddd45629d · outbound

This paper cites Memorization without overfitting: Analyzing the training dynamics of large language models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Memorization without overfitting: Analyzing the training dynamics of large language models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.492847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26fa64ab-eb27-4147-be49-ab9e4ec20298 · outbound

This paper cites More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment.

A Lightweight Method to Disrupt Memorized Sequences in LLM More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

Reference 63

Resolution: verified exact; local_arxiv, observed 2026-08-08T20:08:57.577008Z

Source-reported events for the cited work

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

Observation 935cca9e-f840-4481-bfcd-ea0a1f113379 · outbound

This paper cites RedPajama: an Open Dataset for Training Large Language Models.

A Lightweight Method to Disrupt Memorized Sequences in LLM RedPajama: an Open Dataset for Training Large Language Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.500140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9330b9f7-81af-4a33-863f-0bf068b527df · outbound

This paper cites Speculative decoding for non–autoregressive neural machine translation.

A Lightweight Method to Disrupt Memorized Sequences in LLM Speculative decoding for non–autoregressive neural machine translation

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:57.989656Z

Source-reported events for the cited work

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

Observation 6c4494c2-3c03-4a81-b066-03fbe3dc81ad · outbound

This paper cites Autonomous data selection with language models for mathematical texts.

A Lightweight Method to Disrupt Memorized Sequences in LLM Autonomous data selection with language models for mathematical texts

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T20:08:57.974016Z

Source-reported events for the cited work

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

Observation d0a22b50-317f-4ca9-880d-f5a3ad805715 · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.

A Lightweight Method to Disrupt Memorized Sequences in LLM Judging llm-as-a-judge with mt-bench and chatbot arena

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:57.511375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51057508-22bd-47cd-981a-bb7996a563b3 · outbound

This paper cites Quantifying and Analyzing Entity-level Memorization in Large Language Models.

A Lightweight Method to Disrupt Memorized Sequences in LLM Quantifying and Analyzing Entity-level Memorization in Large Language Models

Reference 68

Resolution: verified exact; local_arxiv, observed 2026-08-08T20:08:57.550482Z

Source-reported events for the cited work

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

Coverage vector

Reference resolution

Outbound references

Pith citing papers