The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models | Paper Citation Record

Observation 1120c164-7488-4664-85ca-4fbf438e445e · outbound

This paper cites Claude 3.5 Haiku.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Claude 3.5 Haiku

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:31.908685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ac0ad291-b943-4b7f-aff8-0d97845968e3 · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Refusal in Language Models Is Mediated by a Single Direction

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:21.415464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2d946f8-f023-4625-b547-8a7014054ef9 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:21.514409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a2e7c31-63f1-42ca-8690-2bda41246e2e · outbound

This paper cites M., Gebru, T., McMillan-Major, A., and Shmitchell, S.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models M., Gebru, T., McMillan-Major, A., and Shmitchell, S

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:21.608921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f580a8a7-c350-432f-ba64-af27926134bb · outbound

This paper cites International AI Safety Report.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models International AI Safety Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:21.692480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ad6413c-ca38-4253-9d6f-b4d72a3c6489 · outbound

This paper cites Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:21.791321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 886000de-fc3c-4351-89f0-6643d4d00004 · outbound

This paper cites Scaling Trends for Data Poisoning in LLMs.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Scaling Trends for Data Poisoning in LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:21.912083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9b9c65f-78fa-444e-b7cc-4b13f27930f4 · outbound

This paper cites AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:08:28.214450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c4e80fd6-65a9-4c02-8702-34d53eacfb79 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:22.099166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6988fd2-9f17-4e27-8b8c-379ec4742215 · outbound

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

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Unlearn What You Want to Forget: Efficient Unlearning for LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:22.273873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 832ce940-fdea-4612-ae4b-d95effa53a38 · outbound

This paper cites Nvidia hopper h100 gpu: Scaling performance.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Nvidia hopper h100 gpu: Scaling performance

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:31.622181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a2f178f4-81b0-426c-b7b3-2150863bbb87 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:22.557051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

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

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

Reference 13

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

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5973ba8e-421c-490f-be92-ab98e9b809f7 · outbound

This paper cites The language model evaluation harness, 07 2024.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models The language model evaluation harness, 07 2024

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:22.792270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1a61a6d-dca5-4933-8d5b-37778dd21446 · outbound

This paper cites AI Control: Improving Safety Despite Intentional Subversion.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models AI Control: Improving Safety Despite Intentional Subversion

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:22.995530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55da837f-39f7-46d8-a027-490949fd7c54 · outbound

This paper cites Llama3-Jailbreak.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Llama3-Jailbreak

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:31.227026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7ad5662e-e8c2-4d09-8da7-ae692f5e7bf1 · outbound

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

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W., et al

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:23.146465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf9bcd0b-aae7-4d5e-8267-4670cb0a4a33 · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:23.292461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a92ffb7e-80dc-400f-bbf3-ac1b6d775d14 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:23.391760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd353d43-b1bd-435a-ae9f-85c017eed29b · outbound

This paper cites PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:23.564199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 352a5d82-6d73-484d-9cb6-3804917ee570 · outbound

This paper cites F reebase QA : A new factoid QA data set matching trivia-style question-answer pairs with F reebase.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models F reebase QA : A new factoid QA data set matching trivia-style question-answer pairs with F reebase

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:23.681078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1afc77e5-09fe-408b-b5bd-5c625a180580 · outbound

This paper cites H., Gonzalez, J.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models H., Gonzalez, J

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:23.731584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 111021dd-05f6-465a-b48e-2376af7f3472 · outbound

This paper cites LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:23.851271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2280816b-8463-4404-9e0c-8b0164984894 · outbound

This paper cites D., Dombrowski, A.-K., Goel, S., Mukobi, G., Helm-Burger, N., Lababidi, R., Justen, L., Liu, A.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models D., Dombrowski, A.-K., Goel, S., Mukobi, G., Helm-Burger, N., Lababidi, R., Justen, L., Liu, A

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:30.942460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 50eac644-d17e-4d9a-ba28-d2d59f876247 · outbound

This paper cites DeepSeek-V3 Technical Report.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models DeepSeek-V3 Technical Report

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:24.047540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ea0ff8e-649f-4dd5-b828-82b9e3177e3a · outbound

This paper cites Y., Xu, X., Li, H., et al.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Y., Xu, X., Li, H., et al

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:30.682711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 28e14957-bee0-429e-8e76-69e286284121 · outbound

This paper cites Robustifying Safety-Aligned Large Language Models through Clean Data Curation.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Robustifying Safety-Aligned Large Language Models through Clean Data Curation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:24.224530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc176058-7916-427c-9821-47c18458f475 · outbound

This paper cites The Llama 3 Herd of Models.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models The Llama 3 Herd of Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:24.372190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a20c0923-a7d3-4909-9505-32063fedcef5 · outbound

This paper cites Simple probes can catch sleeper agents.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Simple probes can catch sleeper agents

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:30.381044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 13cb5077-d5cb-4ba5-85fb-667761a8ae04 · outbound

This paper cites The Llama 4 herd: The beginning of a new era of natively multimodal intelligence , 4 2025.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models The Llama 4 herd: The beginning of a new era of natively multimodal intelligence , 4 2025

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:30.180180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fe4c76cf-ebd8-4afd-ae44-a2f50d4a222a · outbound

This paper cites Meta-Llama-3.1-405B-Instruct-FP8.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Meta-Llama-3.1-405B-Instruct-FP8

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:29.869883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 16007f28-dc4b-4816-bd66-e37a4b4f1d7e · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Steering Llama 2 via Contrastive Activation Addition

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:24.936532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8eba7f8-d6d3-4b31-94bd-f040a8351db8 · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:25.066452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85c5346b-ba8d-4941-990b-0442730a6b0e · outbound

This paper cites Safety Alignment Should Be Made More Than Just a Few Tokens Deep.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:25.207445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f73876e3-38a1-4b77-a097-76c8a011a218 · outbound

This paper cites On Evaluating the Durability of Safeguards for Open-Weight LLMs.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models On Evaluating the Durability of Safeguards for Open-Weight LLMs

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:25.340230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54c28d42-2788-4b57-a859-8cadddef3151 · outbound

This paper cites Fine-Tuning Llama 3.1 405B on a Single Node using Snowflake's Memory-Optimized AI Stack.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Fine-Tuning Llama 3.1 405B on a Single Node using Snowflake's Memory-Optimized AI Stack

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:29.647575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3dc08b09-77a0-43e2-9b87-a462beb708a1 · outbound

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

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Representation noising: A defence mechanism against harmful finetuning

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:29.394827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 181d898d-914b-41c8-9b9c-935c46d88568 · outbound

This paper cites Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:25.826332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0c1b660-dad8-498d-a439-ed05a6c1254f · outbound

This paper cites Extracting Unlearned Information from LLMs with Activation Steering.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Extracting Unlearned Information from LLMs with Activation Steering

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:25.932155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4be6ed6-a8a9-4ab0-b322-4e2504ba7764 · outbound

This paper cites Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:26.082684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdea7963-731f-438a-b589-b37cbb974ff9 · outbound

This paper cites ``Do anything now": Characterizing and evaluating in-the-wild jailbreak prompts on large language models.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models ``Do anything now": Characterizing and evaluating in-the-wild jailbreak prompts on large language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:29.073194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4ac759a4-72b2-4efc-af61-c87eed830fd2 · outbound

This paper cites A strong REJECT for empty jailbreaks.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models A strong REJECT for empty jailbreaks

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:28.813896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f87b89ab-3b43-4f80-b269-6f3f7885f2de · outbound

This paper cites Tamper-Resistant Safeguards for Open-Weight LLMs.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Tamper-Resistant Safeguards for Open-Weight LLMs

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:26.524698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92f0fd53-061e-41d5-8aac-6a7120bf7ffe · outbound

This paper cites CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:26.642025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29fe0c83-d3e8-4741-ba29-4c034c4cb904 · outbound

This paper cites Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:26.789070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a8ffb86-b260-4131-9c8e-48256d090a45 · outbound

This paper cites Jailbroken: How does LLM safety training fail? Advances in Neural Information Processing Systems, 36: 0 80079--80110, 2023.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Jailbroken: How does LLM safety training fail? Advances in Neural Information Processing Systems, 36: 0 80079--80110, 2023

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:28.674253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e25a9167-960c-4e8a-a439-d194c3dd837b · outbound

This paper cites HuggingFace's Transformers: State-of-the-art Natural Language Processing.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models HuggingFace's Transformers: State-of-the-art Natural Language Processing

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:27.046418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e64c3baf-ec14-407b-bd1c-46f386e00ef6 · outbound

This paper cites Qwen2.5 Technical Report.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Qwen2.5 Technical Report

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:27.154764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4ba3406-b5ce-4cd3-8429-d142fa3fbbae · outbound

This paper cites Large language model unlearning.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Large language model unlearning

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:28.555342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9e8c5922-5c05-4fca-b442-b39c67a7c7ef · outbound

This paper cites B., and Kang, D.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models B., and Kang, D

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:08:28.404226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c04afad8-82fe-4773-8d67-97a4c6c89e56 · outbound

This paper cites PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:27.545460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4777db18-432d-4d4b-b08a-62bbc6266ced · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:27.669576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68077c9f-5d32-44c1-bc49-2682f116fb91 · outbound

This paper cites write newline.

The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models write newline

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T19:08:27.776380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers