Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation | Paper Citation Record

Observation e65c18f2-faa2-4d3d-b5b0-2b7092dfa637 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.240046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a202d84-0c97-4bb1-b685-2d4d6adbcab1 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.325795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 444107dd-de74-4159-b95b-a670c2478fb7 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Constitutional AI: Harmlessness from AI Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.448232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88d6aace-017c-430c-9f67-184932d69a17 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.767093Z

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 30b9802b-c9f1-4c0e-bfc2-46c455192534 · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation On the Opportunities and Risks of Foundation Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.617300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02cb49fa-74e4-4e07-a063-470147ef71b4 · outbound

This paper cites Choquette-Choo, Daniel Paleka, Will Pearce, Hyrum Anderson, Andreas Terzis, Kurt Thomas, and Florian Tramèr.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Choquette-Choo, Daniel Paleka, Will Pearce, Hyrum Anderson, Andreas Terzis, Kurt Thomas, and Florian Tramèr

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.620368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8bfc56b-11d7-40ec-ae64-f31441799312 · outbound

This paper cites Pappas, and Eric Wong.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Pappas, and Eric Wong

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:26:14.759006Z

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 6ddbaa36-1a8e-4753-a0cb-f1f1a5097ff2 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.750722Z

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 531a0242-9127-4b39-9423-4cd345f196ce · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.631030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 476dc5b1-9d65-4071-a5d5-c515f8dd0743 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.633838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4942d2f7-4109-44a6-875d-4337cbeef09b · outbound

This paper cites Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.636474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e14f1808-760f-4f9d-9e25-0064345434c5 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.639279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cdc94e7-169b-41ab-9e61-63d88ead5892 · outbound

This paper cites COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.641819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80b1ca02-e5b2-4eee-9478-02fdb5d7fc13 · outbound

This paper cites Spear Phishing With Large Language Models.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Spear Phishing With Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.644775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98e29875-b7c1-437f-85a8-100450f892cc · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.647771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e4f2b11-53a5-4094-8815-5e9e01119140 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.737212Z

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 c6f50e58-8a14-4848-87c0-f017685c0b7d · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.729005Z

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 87c3da8a-2bd1-4af8-98b4-e89550e2d730 · outbound

This paper cites Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.657815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b40b8ec5-7e71-45ec-bedd-8243e5ef1417 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.660236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b48f360-31bb-43ea-974a-bc0199787763 · outbound

This paper cites Rittichier, and Arjan Durresi.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Rittichier, and Arjan Durresi

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.662534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e73887ee-08c2-40a3-a43c-aac12429632a · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.665283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94c0eb51-f047-4d71-8efb-c7589c1f0868 · outbound

This paper cites Model-Editing-Based Jailbreak against Safety-aligned Large Language Models.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Model-Editing-Based Jailbreak against Safety-aligned Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.667591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42b7747e-964d-4fe7-b669-fb29a6f538a6 · outbound

This paper cites Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.670577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6db6c64f-ac0e-4da1-992b-425d213778a7 · outbound

This paper cites TruthfulQA: Measuring How Models Mimic Human Falsehoods.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation TruthfulQA: Measuring How Models Mimic Human Falsehoods

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.673300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdf684ec-85ff-47f2-9438-2d466cb5b72c · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 26

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T19:26:14.715425Z

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 68e302d3-e619-4d0b-84c4-3b73a9b0e679 · outbound

This paper cites The Llama 3 Herd of Models.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation The Llama 3 Herd of Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.678386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73850077-4b26-41fa-a24e-18ed6395c167 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.707705Z

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 213609da-1b1c-4db5-a740-f181633f182b · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.699821Z

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 2c166ecd-6c9c-4812-953d-a714f858e181 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.691654Z

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 01691c5f-dae3-40c1-9116-06b610c643ec · outbound

This paper cites Decoding Secret Memorization in Code LLMs Through Token-Level Characterization.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Decoding Secret Memorization in Code LLMs Through Token-Level Characterization

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.688117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3d6dce4-9beb-45f8-9a67-f8cd306c2940 · outbound

This paper cites GPT-4 Technical Report.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation GPT-4 Technical Report

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.691187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64cbc338-cbb8-4047-ac27-1d1d234b21d8 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.684118Z

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 714362e4-ee54-4d44-9a9f-d4e5159de77e · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.676617Z

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 a3edde7a-2b09-4096-9e4b-c3d793d59ec3 · outbound

This paper cites Universal Jailbreak Backdoors from Poisoned Human Feedback.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.702267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 153125d9-9a68-44fb-ae2f-33c5cd59c40e · outbound

This paper cites SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.705071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70402ed4-0f5f-4170-b963-4ad0be384ac7 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.660638Z

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 a85a7e06-bc5f-4fb8-90b7-1f3bff35dfed · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.710725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56e86c98-86db-4e90-9e14-86e48abcbd8e · outbound

This paper cites Adversarial Attacks and Defenses in Large Language Models: Old and New Threats.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Adversarial Attacks and Defenses in Large Language Models: Old and New Threats

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.716377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0fae038-732b-47ca-9473-9237fc0effa6 · outbound

This paper cites Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.718850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfd7c191-22a8-4785-afc3-458679be44a1 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.647814Z

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 36edf4a4-93eb-44fb-bf6a-913a69bd8446 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.723589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1c4b421-96e4-4c44-a26b-d25cac4cfb86 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.635425Z

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 7c772fc0-2e04-47b0-a9ff-5da75ae40362 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.627959Z

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 e43774cb-6eaa-4dcc-b7f2-7580eb4a6769 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.730532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da060de6-3b05-48f5-8992-3716a41bfc7f · outbound

This paper cites Gomez, Łukasz Kaiser, and Illia Polosukhin.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Gomez, Łukasz Kaiser, and Illia Polosukhin

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.733803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 353eeb47-4bf9-4bcf-b914-8dd221df76fc · outbound

This paper cites Poisoning Language Models During Instruction Tuning.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Poisoning Language Models During Instruction Tuning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.736202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e13a7e2d-232a-4f9e-9cdb-8fb90bdbf0f4 · outbound

This paper cites Poisoning Attacks against Recommender Systems: A Survey.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Poisoning Attacks against Recommender Systems: A Survey

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:26:14.151515Z

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 0a8f1628-907c-4c60-a507-6016e1d7eea4 · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Finetuned Language Models Are Zero-Shot Learners

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.741057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78c43e03-bdbb-458f-83aa-5413134e33b9 · outbound

This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.743717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f389e0b7-354a-4671-bdfb-2bbe5d8459d3 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.746263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4fbffae-b71b-463c-99a2-76741c84795f · outbound

This paper cites Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-08-06T19:26:14.125247Z

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 0e7a2ca2-816b-4295-9c41-9eeadba19a99 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.751199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adf00763-98f3-4885-96fc-cc9efec81ba4 · outbound

This paper cites Qwen2 Technical Report.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Qwen2 Technical Report

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.753557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7ee0b76-e1ea-426c-b837-ad7777a81516 · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Low-Resource Languages Jailbreak GPT-4

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.755908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 314cba2b-a856-4c3b-89a3-5eb01feec2ea · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.758637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 041659d5-19be-4c6b-a56d-f0db0a4fc0b7 · outbound

This paper cites When LLMs Meet Cybersecurity: A Systematic Literature Review.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation When LLMs Meet Cybersecurity: A Systematic Literature Review

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.760965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adb8111b-9767-47ee-805a-65a144a3ac4c · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.763688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 844513cb-37d2-4861-9209-5cd40fa6cf9e · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.766148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dd113a5-6f02-49bb-b354-1774b536c7dc · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.768941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7dc684a-6fcc-421b-843b-5c36214d6415 · outbound

This paper cites Understanding the Effectiveness of Coverage Criteria for Large Language Models: A Special Angle from Jailbreak Attacks.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Understanding the Effectiveness of Coverage Criteria for Large Language Models: A Special Angle from Jailbreak Attacks

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.771379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a23e8d93-7f7b-4d19-8c45-61b2b66b355d · outbound

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

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.774858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1681ef50-917c-4518-b035-aac0e19e9642 · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.610511Z

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 5bd1987f-b35d-4ec5-bcff-7fa264b0a7be · outbound

This paper cites an unresolved cited work.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:26:14.601969Z

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 26d41793-0f18-404f-ae25-3e4c53e3b453 · outbound

This paper cites Hacking is illegal and unethical, and I would never do anything that could put someone’s security at risk.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Hacking is illegal and unethical, and I would never do anything that could put someone’s security at risk

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:26:14.593579Z

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 8c34e16b-35ee-460b-b07f-cf5d67bd9f90 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Proximal Policy Optimization Algorithms

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.713457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61ff9eb1-732c-465e-9779-3fb2647bd335 · outbound

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

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.373964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afc78d83-20d1-4167-82b1-cbaad99b9178 · outbound

This paper cites In The Eleventh International Conference on Learning Representations.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation In The Eleventh International Conference on Learning Representations

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T19:26:14.668413Z

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 f5ba8e02-9b42-4f11-a9f4-f1c4444f7204 · outbound

This paper cites Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation.

Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T19:26:13.652637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers