Paper Citation Record · LEDGER

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

As of 21 August 2026, this Paper Citation Record lists 74 of 74 outbound references and 3 inbound Pith citation observations for arXiv:2505.12038.

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

pith.paper-citation-record.v1
2505.12038 v1

Coverage vector

measured 74 of 74 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:48:09.637499Z

measured 77 of 77 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T22:05:50.798330Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-10T07:16:54.724748Z

Reference resolution

74 of 74 outbound references displayed

verified exact0
verified fuzzy59
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 06ffc698-e179-4fb5-922c-d448b4db6be2 · outbound

This paper cites write newline.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:09.358653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46a546d9-51bd-4dad-913a-cf81f75af7fb · outbound

This paper cites L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.552109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0bdb69e6-d1e0-4f7d-905f-288b38f35958 · outbound

This paper cites Claude, 2023.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Claude, 2023

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.539605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 85979a93-d15b-42b4-ae5e-20fe352ef81b · outbound

This paper cites A general language assistant as a laboratory for alignment.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets A general language assistant as a laboratory for alignment

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.526647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 184b9299-358d-45fb-89fb-9c87f5706d87 · outbound

This paper cites Constitutional AI: harmlessness from AI feedback.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Constitutional AI: harmlessness from AI feedback

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.514850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7de6123d-b268-4f9c-8f53-370d9805674e · outbound

This paper cites D., and Poria, S.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets D., and Poria, S

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.502975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 38d03236-9914-44df-918c-960d9bfc47f6 · outbound

This paper cites Safety-tuned llamas: Lessons from improving the safety of large language models that follow instructions.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Safety-tuned llamas: Lessons from improving the safety of large language models that follow instructions

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.488195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fa1086ee-255c-4616-a977-f2ea6ed82add · outbound

This paper cites J., and Wong, E.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets J., and Wong, E

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.477575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation acd18528-edfc-427c-8929-2722a9c72dca · outbound

This paper cites and Kwok, J.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets and Kwok, J

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.465787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e48b2130-7171-4588-98e5-f23f26cb93a0 · outbound

This paper cites and Kwok, J.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets and Kwok, J

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.454447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a5e6fff1-e35f-43c0-a540-53a4dd24305f · outbound

This paper cites and Kwok, J.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets and Kwok, J

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.442875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7bfa643f-d42e-46fe-8e9a-1b8f1e72874b · outbound

This paper cites an unresolved cited work.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:48:10.428658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f205107a-4ad6-44de-bda6-b0db28b9257a · outbound

This paper cites Training verifiers to solve math word problems.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Training verifiers to solve math word problems

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.416587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2c527ac9-ed9f-4cff-96fa-1d918fb5ad4a · outbound

This paper cites Or-bench: An over-refusal benchmark for large language models.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Or-bench: An over-refusal benchmark for large language models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.405043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 26e499eb-1a8c-4219-a467-bbc9ad733bd2 · outbound

This paper cites Safe RLHF: safe reinforcement learning from human feedback.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Safe RLHF: safe reinforcement learning from human feedback

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.392035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1eaf2eb9-2079-4c79-8a6a-f6634c713ea2 · outbound

This paper cites and Alistarh, D.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets and Alistarh, D

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.380491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 555b25f4-bb92-44bf-8776-8b2c71721910 · outbound

This paper cites an unresolved cited work.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:48:10.368777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ea189a60-db91-41a0-8066-3b4fc6fbeb45 · outbound

This paper cites SAMS um corpus: A human-annotated dialogue dataset for abstractive summarization.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets SAMS um corpus: A human-annotated dialogue dataset for abstractive summarization

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.356192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 95789653-7df5-420e-a3fe-1b82bde2546f · outbound

This paper cites T., Zhang, Y., and Wang, M.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets T., Zhang, Y., and Wang, M

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.341288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a6018676-ad8c-484c-aaa9-0ac424d8ea63 · outbound

This paper cites T., and Zhang, Y.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets T., and Zhang, Y

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.329363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5e4fff59-0fa7-4b7a-9903-576cdf5403ed · outbound

This paper cites T., and Zhang, Y.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets T., and Zhang, Y

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.315625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 43cd4c80-b192-454f-8046-bc851f89d9f0 · outbound

This paper cites The llama 3 herd of models.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets The llama 3 herd of models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.301025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 720004a4-0041-4c7b-8616-21c82f81bc20 · outbound

This paper cites and Stork, D.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets and Stork, D

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.287671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7ba6578d-84b8-4c50-9955-cce397c50853 · outbound

This paper cites Measuring massive multitask language understanding.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Measuring massive multitask language understanding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:09.448267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2ad24bc-93d6-47fc-b0a2-dddc0226617e · outbound

This paper cites Safe lo RA : The silver lining of reducing safety risks when finetuning large language models.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Safe lo RA : The silver lining of reducing safety risks when finetuning large language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.269461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d72c5881-5d81-4354-8c44-a7ef961ce7f0 · outbound

This paper cites J., Shen, Y., Wallis, P., Allen - Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets J., Shen, Y., Wallis, P., Allen - Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:09.456931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76a65fbe-7c41-4701-9911-e6b59e03fef1 · outbound

This paper cites Antidote: Post-fine-tuning safety alignment for large language models against harmful fine-tuning.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Antidote: Post-fine-tuning safety alignment for large language models against harmful fine-tuning

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.250159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9b612919-b420-4318-b7e0-a888c7aa8687 · outbound

This paper cites F., and Liu, L.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets F., and Liu, L

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.238480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation eafd6c8f-d5e5-4ab3-b7f8-2ee15ab700fe · outbound

This paper cites F., and Liu, L.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets F., and Liu, L

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.224298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 421020db-c577-4b03-a1a5-a29f28011a67 · outbound

This paper cites Vaccine: Perturbation-aware alignment for large language models against harmful fine-tuning attack.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Vaccine: Perturbation-aware alignment for large language models against harmful fine-tuning attack

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.211907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d2f37b53-3550-42a9-afb8-42fd5393194d · outbound

This paper cites F., and Liu, L.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets F., and Liu, L

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.191379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5cbf0e13-88cc-474e-ab1c-1ab6cdcd4e31 · outbound

This paper cites Catastrophic jailbreak of open-source llms via exploiting generation.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Catastrophic jailbreak of open-source llms via exploiting generation

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.175610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cab5168c-3bb7-448f-af79-b83b531848be · outbound

This paper cites Accurate post training quantization with small calibration sets.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Accurate post training quantization with small calibration sets

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.161514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 85ff3f11-f9ff-41bc-ac49-f9539ff67c26 · outbound

This paper cites Beavertails: Towards improved safety alignment of LLM via a human-preference dataset.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Beavertails: Towards improved safety alignment of LLM via a human-preference dataset

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.149895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 37b644d9-66d7-4628-8751-8769ea7c72f7 · outbound

This paper cites S., and Solla, S.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets S., and Solla, S

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.136499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c547a46f-67bd-4ed5-a71e-ed0338aa9c0b · outbound

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

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Rouge: A package for automatic evaluation of summaries

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:09.494983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2a75962-a90a-488e-b8fe-e3766bde06ed · outbound

This paper cites Efficient combinatorial optimization for word-level adversarial textual attack.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Efficient combinatorial optimization for word-level adversarial textual attack

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.112619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cc8ff391-bddf-4cd1-84ac-f3792dc28994 · outbound

This paper cites Effective and imperceptible adversarial textual attack via multi-objectivization.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Effective and imperceptible adversarial textual attack via multi-objectivization

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.095666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ff741e80-04be-4925-a69e-d9c7d707bc43 · outbound

This paper cites Autodan: Generating stealthy jailbreak prompts on aligned large language models.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Autodan: Generating stealthy jailbreak prompts on aligned large language models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.081438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8a3fce4b-58c4-436d-944e-d3915437abf8 · outbound

This paper cites Jailbreaking chatgpt via prompt engineering: An empirical study.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Jailbreaking chatgpt via prompt engineering: An empirical study

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.069156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8ce2d8e3-a788-4de0-b3cf-19b558887bb9 · outbound

This paper cites and Hutter, F.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets and Hutter, F

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:09.515691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b48d144-5f21-43e5-a36d-da1e2fa5516c · outbound

This paper cites Large language models can be guided to evade ai-generated text detection.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Large language models can be guided to evade ai-generated text detection

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.048517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 12f0d60f-a0a8-4de2-8900-5d89404a427b · outbound

This paper cites Less is more: Understanding word-level textual adversarial attack via n-gram frequency descend.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Less is more: Understanding word-level textual adversarial attack via n-gram frequency descend

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.036850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 086aa09e-52d0-428c-9a82-d9f5c532ad10 · outbound

This paper cites Training overhead ratio: A practical reliability metric for large language model training systems.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Training overhead ratio: A practical reliability metric for large language model training systems

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:10.024008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5c5d159b-7570-46a2-934a-4c80b0ceaf2b · outbound

This paper cites an unresolved cited work.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:48:10.009449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation baa0e1a6-2158-4c23-be02-da1a495353e6 · outbound

This paper cites Training language models to follow instructions with human feedback.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Training language models to follow instructions with human feedback

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:09.534885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89f38a6a-2757-427a-ac4d-a5f79d4df568 · outbound

This paper cites Fine-tuning now available for gpt-4o, 2024.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Fine-tuning now available for gpt-4o, 2024

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.989266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c5cc1688-fbb6-4376-9516-d02af1e946e6 · outbound

This paper cites Instruction tuning with GPT-4.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Instruction tuning with GPT-4

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.979184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3409dd57-7632-4bc2-a924-08eab1087789 · outbound

This paper cites Fine-tuning aligned language models compromises safety, even when users do not intend to! In The Twelfth International Conference on Learning Representations, 2024.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Fine-tuning aligned language models compromises safety, even when users do not intend to! In The Twelfth International Conference on Learning Representations, 2024

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.968712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1f14dfad-4f74-48a4-85cf-db3325442932 · outbound

This paper cites D., Ermon, S., and Finn, C.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets D., Ermon, S., and Finn, C

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.955652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3eff96cc-2f75-460d-a807-f4aff180614e · outbound

This paper cites Modelgrow: Continual text-to-video pre-training with model expansion and language understanding enhancement.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Modelgrow: Continual text-to-video pre-training with model expansion and language understanding enhancement

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.942964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 50cf077a-867a-4fe9-96a3-029a9f7074d3 · outbound

This paper cites Representation noising: A defence mechanism against harmful finetuning.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Representation noising: A defence mechanism against harmful finetuning

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.929236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation febc9c75-3f5d-47de-803c-9ce89aac5cfb · outbound

This paper cites an unresolved cited work.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:48:09.916189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9c59bfa1-d2d5-4804-8972-aa168d140938 · outbound

This paper cites do anything now.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets do anything now

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.903027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b8406427-e273-49eb-b614-0c6f8059cd1e · outbound

This paper cites Axiomatic attribution for deep networks.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Axiomatic attribution for deep networks

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.889922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 91529f78-8d93-485c-9738-0e1c54cd2af4 · outbound

This paper cites Intriguing properties of neural networks.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Intriguing properties of neural networks

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:09.570773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a816b57d-fada-4e37-aa60-da5529643cde · outbound

This paper cites an unresolved cited work.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:09.574479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cfe80fa-a50d-485d-af6d-e2df5fa984af · outbound

This paper cites Llama 2: Open foundation and fine-tuned chat models.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Llama 2: Open foundation and fine-tuned chat models

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.870472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5469cc26-d445-4d2f-afe1-f8c12451fa4d · outbound

This paper cites Backdooralign: Mitigating fine-tuning based jailbreak attack with backdoor enhanced safety alignment.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Backdooralign: Mitigating fine-tuning based jailbreak attack with backdoor enhanced safety alignment

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.858553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4bbcd51a-bee2-4bd9-86d6-e7f46c1013ad · outbound

This paper cites W., Lester, B., Du, N., Dai, A.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets W., Lester, B., Du, N., Dai, A

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T20:48:09.584046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34a1d094-073c-4a9d-947a-7c08c09d0c42 · outbound

This paper cites an unresolved cited work.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Unresolved cited work

Reference 61

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:48:09.840610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ca1bf601-9710-4d28-a6e5-d615025475f9 · outbound

This paper cites T., and Zhang, Y.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets T., and Zhang, Y

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.828375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e111a9b0-e93e-441d-9842-e85a989af69c · outbound

This paper cites Open the eyes of mpnn: Vision enhances mpnn in link prediction, 2025.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Open the eyes of mpnn: Vision enhances mpnn in link prediction, 2025

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.816424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4352e134-1c60-455a-b689-5b751316a200 · outbound

This paper cites Backdoor graph condensation.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Backdoor graph condensation

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.804801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f0d71694-5392-408c-9660-75b5f1c6470b · outbound

This paper cites Tf-dcon: Leveraging large language models (llms) to empower training-free dataset condensation for content-based recommendation, 2025.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Tf-dcon: Leveraging large language models (llms) to empower training-free dataset condensation for content-based recommendation, 2025

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.790900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 00bc88b6-1acf-4493-aa6b-e2118a33cd38 · outbound

This paper cites RLCD: reinforcement learning from contrastive distillation for LM alignment.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets RLCD: reinforcement learning from contrastive distillation for LM alignment

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.778858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1bc3c7b1-5acf-445b-969f-027fc208a9e9 · outbound

This paper cites Y., Zhao, X., and Lin, D.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Y., Zhao, X., and Lin, D

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.765742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e73d58be-004b-41e2-8c42-1806d6eac4fb · outbound

This paper cites NLSR: neuron-level safety realignment of large language models against harmful fine-tuning.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets NLSR: neuron-level safety realignment of large language models against harmful fine-tuning

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.755306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7e91603c-a9ac-456e-83f9-cd977e6019ac · outbound

This paper cites an unresolved cited work.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:48:09.744809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c731b779-da08-4469-8551-bb95f636ea28 · outbound

This paper cites GPT-4 is too smart to be safe: Stealthy chat with llms via cipher.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets GPT-4 is too smart to be safe: Stealthy chat with llms via cipher

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.733690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 86e8a6a8-443d-4d40-beb8-24f16c2d4e51 · outbound

This paper cites Removing RLHF protections in GPT-4 via fine-tuning.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Removing RLHF protections in GPT-4 via fine-tuning

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.722035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 648c4e5a-e75e-4bf7-82f3-634c0cf6e84d · outbound

This paper cites P., Zhang, H., Gonzalez, J.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets P., Zhang, H., Gonzalez, J

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.709539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 70f4184b-93f8-4cff-b3e4-157072b49626 · outbound

This paper cites Model tailor: Mitigating catastrophic forgetting in multi-modal large language models.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Model tailor: Mitigating catastrophic forgetting in multi-modal large language models

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.696452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e0e6b709-8b36-48fe-a6fc-0777aea92182 · outbound

This paper cites Z., and Fredrikson, M.

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets Z., and Fredrikson, M

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:48:09.683985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

Observation 9df8334b-e98c-4196-b3b4-0d0ce55f9688 · inbound

Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction cites this paper.

Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T22:05:50.798330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa548b6b-122a-4a6b-80d2-7e615c384983 · inbound

Continual Safety Alignment via Gradient-Based Sample Selection cites this paper.

Continual Safety Alignment via Gradient-Based Sample Selection Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-10T07:16:54.726087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1ad72020-6449-47aa-a97c-2bb7e0eae2e0 · inbound

TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment cites this paper.

TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T10:00:09.737616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.