Paper Citation Record · LEDGER

Probing the Robustness of Large Language Models Safety to Latent Perturbations

As of 9 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 4 inbound Pith citation observations for arXiv:2506.16078.

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

pith.paper-citation-record.v1
2506.16078 v1

Coverage vector

measured 53 of 53 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:49:19.347784Z

measured 57 of 57 standing notices

One-hop event checks from named stored sources.

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

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-27T03:24:24.714121Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

53 of 53 outbound references displayed

verified exact0
verified fuzzy13
unresolved40
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 44757a17-c1ea-4f3c-ad97-f022f4781849 · outbound

This paper cites URL https://api.semanticscholar.org/CorpusID:268232499.

Probing the Robustness of Large Language Models Safety to Latent Perturbations URL https://api.semanticscholar.org/CorpusID:268232499

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:12.823540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 718eee71-0ac9-4984-8b4d-27ede5b53529 · outbound

This paper cites GPT-4 Technical Report.

Probing the Robustness of Large Language Models Safety to Latent Perturbations GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:12.948150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28c35c6b-b441-4b2e-a413-138b5172816b · outbound

This paper cites Foundational Challenges in Assuring Alignment and Safety of Large Language Models.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:13.094114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce6cad00-b61a-4956-b815-a592d136e3ce · outbound

This paper cites Refusal in language models is mediated by a single direction.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Refusal in language models is mediated by a single direction

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:49:22.260682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ff69e5cd-8704-47a4-94e4-9cc84f296787 · outbound

This paper cites Qwen Technical Report.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Qwen Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:13.400656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 268798a0-aa0b-4957-9ddf-679229567239 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Constitutional AI: Harmlessness from AI Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:13.523748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19916c45-3fad-4278-b18f-facb56a1446e · outbound

This paper cites Defending Against Unforeseen Failure Modes with Latent Adversarial Training.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Defending Against Unforeseen Failure Modes with Latent Adversarial Training

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:13.652587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a8cbe40-1481-4509-90a3-440ba53a2645 · outbound

This paper cites Jailbreaking black box large language models in twenty queries.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Jailbreaking black box large language models in twenty queries

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:13.760620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8db9b532-ee68-48e0-95c5-0aa7879e17d3 · outbound

This paper cites Probing Latent Subspaces in LLM for AI Security: Identifying and Manipulating Adversarial States.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Probing Latent Subspaces in LLM for AI Security: Identifying and Manipulating Adversarial States

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:13.842722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52f4463e-e514-47a3-8380-78bdbb47f8c5 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Training Verifiers to Solve Math Word Problems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:13.943741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e31ae40-8794-4330-9ebb-36b06ab76392 · outbound

This paper cites Scaling Laws for Adversarial Attacks on Language Model Activations.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Scaling Laws for Adversarial Attacks on Language Model Activations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:14.075962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dac8ef6-6477-455b-bf29-81049e1406ef · outbound

This paper cites Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:14.203220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec9bbdf3-572d-4998-909e-05f08a5733e8 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Explaining and Harnessing Adversarial Examples

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:14.339131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54ed4062-b926-4749-9107-c588f9489a4a · outbound

This paper cites The Llama 3 Herd of Models.

Probing the Robustness of Large Language Models Safety to Latent Perturbations The Llama 3 Herd of Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:14.419356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08f40f92-7bcb-4bdd-900e-d092364a26b1 · outbound

This paper cites MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts.

Probing the Robustness of Large Language Models Safety to Latent Perturbations MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:14.540498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a44650f-67a2-4463-85e3-d59c58693d32 · outbound

This paper cites Flames: Benchmarking Value Alignment of LLMs in Chinese.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Flames: Benchmarking Value Alignment of LLMs in Chinese

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:14.676174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95220e44-bdb4-4e09-8c2f-e2c4eba63848 · outbound

This paper cites Arbitrary style transfer in real-time with adaptive instance normalization.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Arbitrary style transfer in real-time with adaptive instance normalization

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:49:22.138710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cf554321-a7f5-4f89-8968-71a2fe8805f5 · outbound

This paper cites Improving Activation Steering in Language Models with Mean-Centring.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Improving Activation Steering in Language Models with Mean-Centring

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:14.924023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e160b3f4-483a-4f70-8c09-475364f81c59 · outbound

This paper cites Large language model unlearning via embedding-corrupted prompts.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Large language model unlearning via embedding-corrupted prompts

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:49:22.036639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7e486610-471a-4941-b6e0-fd8eec956859 · outbound

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

Probing the Robustness of Large Language Models Safety to Latent Perturbations Autodan: Generating stealthy jailbreak prompts on aligned large language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:49:21.808465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ff108060-af99-4009-a9d4-880f6fa53ce0 · outbound

This paper cites Merge to learn: Efficiently adding skills to language models with model merging.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Merge to learn: Efficiently adding skills to language models with model merging

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:49:21.570220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation faeb8a01-9c95-44ae-9428-54e50b471d98 · outbound

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

Probing the Robustness of Large Language Models Safety to Latent Perturbations Training language models to follow instructions with human feedback

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:15.426561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76f0fe94-24e7-4577-a589-7cde1d0a3520 · outbound

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

Probing the Robustness of Large Language Models Safety to Latent Perturbations Training language models to follow instructions with human feedback

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:49:21.306450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 28760bb7-0e67-4836-bdd1-37e38d88071c · outbound

This paper cites In-context unlearning: Language models as few-shot unlearners.

Probing the Robustness of Large Language Models Safety to Latent Perturbations In-context unlearning: Language models as few-shot unlearners

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:49:21.149432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f0ff625d-af38-4182-b385-564958386640 · outbound

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

Probing the Robustness of Large Language Models Safety to Latent Perturbations Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:15.862324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af8f1517-15e1-4b94-a4e7-822f29993113 · 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.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Fine-tuning aligned language models compromises safety, even when users do not intend to! In The Twelfth International Conference on Learning Representations, 2024

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:49:20.999488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation abb051b1-11fc-4560-94a1-5d911f89b1f6 · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:16.090709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e1364f3-4ddd-4670-9358-11f181162778 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Direct preference optimization: Your language model is secretly a reward model

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:49:20.871420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 99a40b3f-4945-4de1-ab35-7ff78bbae000 · outbound

This paper cites Steering llama 2 via contrastive activation addition.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Steering llama 2 via contrastive activation addition

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:16.288237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f44eefa-c8fa-4b91-9c38-ee6bf5e3db3c · outbound

This paper cites Proximal Policy Optimization Algorithms.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Proximal Policy Optimization Algorithms

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:16.388217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48d5fb51-d013-41a7-8ec0-1afef777e68a · outbound

This paper cites Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:16.506515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef3f9bf9-ed9b-4564-8d7e-a651e0a17486 · outbound

This paper cites C ommonsense QA : A question answering challenge targeting commonsense knowledge.

Probing the Robustness of Large Language Models Safety to Latent Perturbations C ommonsense QA : A question answering challenge targeting commonsense knowledge

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:16.624391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96943394-bc7e-41fe-ac19-93d292110571 · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Qwen2.5: A party of foundation models, September 2024

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:16.769634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56a5d664-4a78-4c63-90de-f10015228f14 · outbound

This paper cites Qwq-32b: Embracing the power of reinforcement learning, March 2025.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Qwq-32b: Embracing the power of reinforcement learning, March 2025

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:16.926076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6398be82-68be-4b45-92bb-41b031c6e0d0 · outbound

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

Probing the Robustness of Large Language Models Safety to Latent Perturbations Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:17.044926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a0367ca-accc-42e2-92cc-c852408c0b1b · outbound

This paper cites Steering Language Models With Activation Engineering.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Steering Language Models With Activation Engineering

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:17.179313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 632f255a-7e6b-4bd0-a1cb-80707deb3485 · outbound

This paper cites A Language Model's Guide Through Latent Space.

Probing the Robustness of Large Language Models Safety to Latent Perturbations A Language Model's Guide Through Latent Space

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:17.308168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b6adedc-a47d-4cdd-96cd-7504bbb58849 · outbound

This paper cites Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:17.484246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5491bab7-e1c9-4d1d-8867-b51f0d8c7339 · outbound

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

Probing the Robustness of Large Language Models Safety to Latent Perturbations Finetuned Language Models Are Zero-Shot Learners

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:17.692465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33c06365-89a2-47d4-9275-e0a54e7cb143 · outbound

This paper cites Robust fine-tuning of zero-shot models.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Robust fine-tuning of zero-shot models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:49:20.692151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7fb5c9af-9b3f-40a6-835c-646d0740e914 · outbound

This paper cites Uncovering safety risks of large language models through concept activation vector.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Uncovering safety risks of large language models through concept activation vector

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:49:20.511936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 167be9c9-28bd-4a7b-a9d7-4d51f7b4efb7 · outbound

This paper cites Qwen2 Technical Report.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Qwen2 Technical Report

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:18.076065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49f6e146-811b-4ee3-bf4c-6b1e275cff48 · outbound

This paper cites Qwen3 Technical Report.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Qwen3 Technical Report

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:18.222192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6800cdc0-9bb0-4750-9704-262036744b00 · outbound

This paper cites A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos.

Probing the Robustness of Large Language Models Safety to Latent Perturbations A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:18.339304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d59debf4-233c-4fbc-9f42-52a40287bbc8 · outbound

This paper cites Yi: Open Foundation Models by 01.AI.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Yi: Open Foundation Models by 01.AI

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:18.489339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9fe87b3-afc9-4e0e-af64-f0dea814d388 · outbound

This paper cites Removing rlhf protections in gpt-4 via fine-tuning.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Removing rlhf protections in gpt-4 via fine-tuning

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:49:20.370575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4def3251-ed86-4529-ae70-b1c3d50e2402 · outbound

This paper cites Controlling large language models through concept activation vectors.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Controlling large language models through concept activation vectors

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:49:20.227249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a6beb801-d181-4c28-9f4d-f4a3f64d9911 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Representation Engineering: A Top-Down Approach to AI Transparency

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:18.890265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 241aea52-f36e-4245-b5bf-9d3cdec25e84 · outbound

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

Probing the Robustness of Large Language Models Safety to Latent Perturbations Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:19.031485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb83993d-61ca-448b-af60-7ad1dffd570c · outbound

This paper cites write newline.

Probing the Robustness of Large Language Models Safety to Latent Perturbations write newline

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:19.162518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 082b78b0-2268-469f-b2df-6d916aae5b3b · outbound

This paper cites @esa (Ref.

Probing the Robustness of Large Language Models Safety to Latent Perturbations @esa (Ref

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:19.235253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa129338-5c1c-4bc9-8ebd-ef596cbd1265 · outbound

This paper cites an unresolved cited work.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:19.294952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bfd156c-ad65-42cc-85e1-1b0b4660c411 · outbound

This paper cites Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models.

Probing the Robustness of Large Language Models Safety to Latent Perturbations Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:19.347784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 02cf7c9a-d832-48d7-b219-06c3e5ffc297 · inbound

The Impact of Off-Policy Training Data on Probe Generalisation cites this paper.

The Impact of Off-Policy Training Data on Probe Generalisation Probing the Robustness of Large Language Models Safety to Latent Perturbations

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T20:30:11.710099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 886bd8ff-0cd4-488a-9940-59e25931abd6 · inbound

Do Linear Probes Generalize Better in Persona Coordinates? cites this paper.

Do Linear Probes Generalize Better in Persona Coordinates? Probing the Robustness of Large Language Models Safety to Latent Perturbations

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:51:23.072108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a18f57df-b40a-408d-8aba-c97a249e2be6 · inbound

Do Linear Probes Generalize Better in Persona Coordinates? cites this paper.

Do Linear Probes Generalize Better in Persona Coordinates? Probing the Robustness of Large Language Models Safety to Latent Perturbations

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:07:40.576154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9d59673f-1414-478d-b516-68d1df279595 · inbound

Do Activation Monitors Survive Model Updates? Benchmarking, Predicting, and Repairing Activation-Monitor Staleness cites this paper.

Do Activation Monitors Survive Model Updates? Benchmarking, Predicting, and Repairing Activation-Monitor Staleness Probing the Robustness of Large Language Models Safety to Latent Perturbations

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-06-27T03:30:26.963521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.