Paper Citation Record · LEDGER

UCD: Unlearning in LLMs via Contrastive Decoding

As of 8 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 3 inbound Pith citation observations for arXiv:2506.12097.

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

pith.paper-citation-record.v1
2506.12097 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:22:59.910903Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T23:21:28.103297Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T19:16:01.067628Z

Reference resolution

35 of 35 outbound references displayed

verified exact0
verified fuzzy3
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 57c2c9b5-a185-4097-9142-d86689e87ec8 · outbound

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

UCD: Unlearning in LLMs via Contrastive Decoding Unlearn What You Want to Forget: Efficient Unlearning for LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.816733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 248102ac-f18c-4251-8635-e5581f8cd5ee · outbound

This paper cites Regulation (eu) 2016/679 of the european parliament and of the council of 27 april.

UCD: Unlearning in LLMs via Contrastive Decoding Regulation (eu) 2016/679 of the european parliament and of the council of 27 april

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:23:00.126703Z

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 f0e6c3cb-3f80-4096-ac38-131b40c56e5f · outbound

This paper cites The Curious Case of Neural Text Degeneration.

UCD: Unlearning in LLMs via Contrastive Decoding The Curious Case of Neural Text Degeneration

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.825555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd170ef7-ebf7-43e9-b8c2-33c187d041dc · outbound

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

UCD: Unlearning in LLMs via Contrastive Decoding Knowledge Unlearning for Mitigating Privacy Risks in Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.834998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34885555-89a7-414f-907e-9add76874f60 · outbound

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

UCD: Unlearning in LLMs via Contrastive Decoding SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.838143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 329dd458-b6ee-4f3c-bbaa-24217d06738c · outbound

This paper cites Copyright Violations and Large Language Models.

UCD: Unlearning in LLMs via Contrastive Decoding Copyright Violations and Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.843628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49db2240-9d9d-4762-8b4f-65c67d34b511 · outbound

This paper cites Australia to consider european-style right to be forgotten privacy laws.The Guardian (Jan.

UCD: Unlearning in LLMs via Contrastive Decoding Australia to consider european-style right to be forgotten privacy laws.The Guardian (Jan

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:23:00.118408Z

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 d94c10cb-cbb0-474f-b455-2d2713f591e9 · outbound

This paper cites Privacy Adhering Machine Un-learning in NLP.

UCD: Unlearning in LLMs via Contrastive Decoding Privacy Adhering Machine Un-learning in NLP

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.849083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cdbc6cf-2bed-42a4-8f4a-2eca7ff878a9 · outbound

This paper cites Exact unlearning of finetuning data via model merging at scale.

UCD: Unlearning in LLMs via Contrastive Decoding Exact unlearning of finetuning data via model merging at scale

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:23:00.110488Z

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 4a3f03c1-5b21-47be-a4e4-6e898f273136 · outbound

This paper cites The Approximate Fisher Influence Function: Faster Estimation of Data Influence in Statistical Models.

UCD: Unlearning in LLMs via Contrastive Decoding The Approximate Fisher Influence Function: Faster Estimation of Data Influence in Statistical Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.854416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 322db20a-563d-447e-bcf3-eea808321189 · outbound

This paper cites The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning.

UCD: Unlearning in LLMs via Contrastive Decoding The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.858064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 255544c7-6660-4267-a05d-4fbcfec973f8 · outbound

This paper cites URL https://aclanthology.org/2023.acl-long.687/.

UCD: Unlearning in LLMs via Contrastive Decoding URL https://aclanthology.org/2023.acl-long.687/

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.860769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5895ce17-df25-4108-87dd-1bf18d44e958 · outbound

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

UCD: Unlearning in LLMs via Contrastive Decoding Large Language Model Unlearning via Embedding-Corrupted Prompts

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.864196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc4782b7-50e4-4a7d-848e-1ebc2bfd9f7d · outbound

This paper cites An Adversarial Perspective on Machine Unlearning for AI Safety.

UCD: Unlearning in LLMs via Contrastive Decoding An Adversarial Perspective on Machine Unlearning for AI Safety

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.866876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e752cda-02d1-4af4-b6ae-b61f71c8710b · outbound

This paper cites Locating and Editing Factual Associations in GPT.

UCD: Unlearning in LLMs via Contrastive Decoding Locating and Editing Factual Associations in GPT

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.870189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0229e49-9182-4556-b063-23278f02ce24 · outbound

This paper cites Fast Model Editing at Scale.

UCD: Unlearning in LLMs via Contrastive Decoding Fast Model Editing at Scale

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.873157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bff8cbd-0953-40ba-9515-f7c8f7be6fcc · outbound

This paper cites A Survey of Machine Unlearning.

UCD: Unlearning in LLMs via Contrastive Decoding A Survey of Machine Unlearning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.875845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78242598-fac4-4a9d-bb21-549d0253b68b · outbound

This paper cites Contrastive Decoding Improves Reasoning in Large Language Models.

UCD: Unlearning in LLMs via Contrastive Decoding Contrastive Decoding Improves Reasoning in Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.878544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41250d86-af8c-4665-a359-52d40c756c20 · outbound

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

UCD: Unlearning in LLMs via Contrastive Decoding In-Context Unlearning: Language Models as Few Shot Unlearners

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.881912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c143aa9-3f8e-440b-8d71-c2a3927530e5 · outbound

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

UCD: Unlearning in LLMs via Contrastive Decoding Rethinking LLM Memorization through the Lens of Adversarial Compression

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.884621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c6d6086-2acf-4e2d-bf5f-454524113818 · outbound

This paper cites Model evaluation for extreme risks.

UCD: Unlearning in LLMs via Contrastive Decoding Model evaluation for extreme risks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.887715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1b168b5-ead6-4261-9e02-2c33268bef52 · outbound

This paper cites Detecting Pretraining Data from Large Language Models.

UCD: Unlearning in LLMs via Contrastive Decoding Detecting Pretraining Data from Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.890884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53dedfd4-d3c9-427d-bd74-50ad5c774532 · outbound

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

UCD: Unlearning in LLMs via Contrastive Decoding MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.893510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69539e73-f8c2-420c-8550-e71b436dc8ce · outbound

This paper cites Guardrail Baselines for Unlearning in LLMs.

UCD: Unlearning in LLMs via Contrastive Decoding Guardrail Baselines for Unlearning in LLMs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.895995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8b48618-9ec6-41d2-b9c0-7b2731102926 · outbound

This paper cites GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment.

UCD: Unlearning in LLMs via Contrastive Decoding GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.901678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 827233c1-a2d2-420b-8c5c-6a47c90fc52f · outbound

This paper cites Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities.

UCD: Unlearning in LLMs via Contrastive Decoding Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.904872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e68cfed9-9054-4469-94ac-37357192de68 · outbound

This paper cites Large Language Model Unlearning.

UCD: Unlearning in LLMs via Contrastive Decoding Large Language Model Unlearning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.907434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ecf4d90-f30f-4c76-8056-cdf97e422faa · outbound

This paper cites an unresolved cited work.

UCD: Unlearning in LLMs via Contrastive Decoding Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:23:00.101723Z

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 8e44b40c-6d6c-40b2-83a1-4d938b5fe952 · outbound

This paper cites Large Scale Knowledge Washing.

UCD: Unlearning in LLMs via Contrastive Decoding Large Scale Knowledge Washing

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.898593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2a137df-ba47-48f6-ade7-9f67f15f0b0c · outbound

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

UCD: Unlearning in LLMs via Contrastive Decoding Open Problems in Machine Unlearning for AI Safety

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.810289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aaa9bff-bac8-42ca-bafb-a768cbbabd67 · outbound

This paper cites Editing Models with Task Arithmetic.

UCD: Unlearning in LLMs via Contrastive Decoding Editing Models with Task Arithmetic

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.828238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c84f387-aa71-418f-8cea-2447f1d53455 · outbound

This paper cites Towards making systems forget with machine unlearning.

UCD: Unlearning in LLMs via Contrastive Decoding Towards making systems forget with machine unlearning

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.813723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d02afec1-a00d-40bb-8752-45c832522f89 · outbound

This paper cites Knowledge Sanitization of Large Language Models.

UCD: Unlearning in LLMs via Contrastive Decoding Knowledge Sanitization of Large Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.831196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 103e6e45-fb35-4abe-a527-3646daba9f93 · outbound

This paper cites Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning.

UCD: Unlearning in LLMs via Contrastive Decoding Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.819768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12dfb38b-4edb-43e2-ad3f-b217c92335d8 · outbound

This paper cites Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs.

UCD: Unlearning in LLMs via Contrastive Decoding Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T04:22:59.840985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation f06d5aa0-ee68-4816-aec3-f5997d1989ce · inbound

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

Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning UCD: Unlearning in LLMs via Contrastive Decoding

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:46:17.078729Z

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 b3da7110-58c7-4b87-a8e8-0c58e8e65a9f · inbound

Divergence Decoding: Inference-Time Unlearning via Auxiliary Models cites this paper.

Divergence Decoding: Inference-Time Unlearning via Auxiliary Models UCD: Unlearning in LLMs via Contrastive Decoding

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-01T19:16:01.069309Z

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 d076171f-e8dc-4c41-8a16-aa5a4a2b3e90 · inbound

Position: The Term "Machine Unlearning" Is Overused in LLMs cites this paper.

Position: The Term "Machine Unlearning" Is Overused in LLMs UCD: Unlearning in LLMs via Contrastive Decoding

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T13:25:44.961912Z

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.