Paper Citation Record · LEDGER

Advancing LLM Safe Alignment with Safety Representation Ranking

As of 19 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 11 inbound Pith citation observations for arXiv:2505.15710.

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

pith.paper-citation-record.v1
2505.15710 v1

Coverage vector

measured 50 of 50 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:15:18.375972Z

measured 61 of 61 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 11 of 11 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:28:42.361096Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T07:53:14.432882Z

Reference resolution

50 of 50 outbound references displayed

verified exact0
verified fuzzy32
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cc41ad3d-ea9b-4498-9424-1c28ce32430b · outbound

This paper cites Foundational challenges in assuring alignment and safety of large language models.

Advancing LLM Safe Alignment with Safety Representation Ranking Foundational challenges in assuring alignment and safety of large language models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.847508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8fcedc20-95b4-44fd-ae1d-6624ccdd3722 · outbound

This paper cites Constitutional ai: Harmlessness from ai feedback, 2022.

Advancing LLM Safe Alignment with Safety Representation Ranking Constitutional ai: Harmlessness from ai feedback, 2022

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.840918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bd145b7d-ecfe-4191-9a68-0afe8a21ed2a · outbound

This paper cites Safeinfer: Context adaptive decoding time safety alignment for large language models.

Advancing LLM Safe Alignment with Safety Representation Ranking Safeinfer: Context adaptive decoding time safety alignment for large language models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.834310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9b4f2425-6ecd-4de2-b7e4-169ff89c6355 · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

Advancing LLM Safe Alignment with Safety Representation Ranking Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.235655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a95981c-7205-4f03-a99f-6c0685003853 · outbound

This paper cites Pappas, Florian Tramer, Hamed Hassani, and Eric Wong.

Advancing LLM Safe Alignment with Safety Representation Ranking Pappas, Florian Tramer, Hamed Hassani, and Eric Wong

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.827732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c260cec5-2926-48f5-b352-de53010be1ec · outbound

This paper cites Finding safety neurons in large language models.

Advancing LLM Safe Alignment with Safety Representation Ranking Finding safety neurons in large language models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.241298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2b1e6a2-1d86-41f8-b6f0-79aa48b80e32 · outbound

This paper cites Safe rlhf: Safe reinforcement learning from human feedback.

Advancing LLM Safe Alignment with Safety Representation Ranking Safe rlhf: Safe reinforcement learning from human feedback

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.820841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bef79a3d-131a-480d-9ff0-5089a1ce3928 · outbound

This paper cites Hierarchical neural story generation.

Advancing LLM Safe Alignment with Safety Representation Ranking Hierarchical neural story generation

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.813974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5e82de10-2706-46b0-907e-02a3a12c1cd0 · outbound

This paper cites Controlling linguistic style aspects in neural language generation.

Advancing LLM Safe Alignment with Safety Representation Ranking Controlling linguistic style aspects in neural language generation

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.807351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d8d63c05-0df6-485c-b4aa-8b231811a896 · outbound

This paper cites Evolving neural turing machines for reward-based learning.

Advancing LLM Safe Alignment with Safety Representation Ranking Evolving neural turing machines for reward-based learning

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.800140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4ff5faf9-998c-4d13-9deb-9f3ec2b9e867 · outbound

This paper cites Measuring mathematical problem solving with the math dataset.

Advancing LLM Safe Alignment with Safety Representation Ranking Measuring mathematical problem solving with the math dataset

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.793287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cf2f1b0f-e39a-49ba-bc7f-8963484a907f · outbound

This paper cites The curious case of neural text degeneration.

Advancing LLM Safe Alignment with Safety Representation Ranking The curious case of neural text degeneration

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.786568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3c067e4f-932f-472e-9bdf-b610902fc184 · outbound

This paper cites Learning to write with cooperative discriminators.

Advancing LLM Safe Alignment with Safety Representation Ranking Learning to write with cooperative discriminators

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.779084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b7270254-4aab-4948-9855-19b980d6df2c · outbound

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

Advancing LLM Safe Alignment with Safety Representation Ranking Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.261712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18652234-1528-4a29-a5b9-14e1212899cd · outbound

This paper cites AI Alignment: A Comprehensive Survey.

Advancing LLM Safe Alignment with Safety Representation Ranking AI Alignment: A Comprehensive Survey

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.265028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29a82d71-3059-4ad4-98a7-e5da9457f925 · outbound

This paper cites Mistral 7B.

Advancing LLM Safe Alignment with Safety Representation Ranking Mistral 7B

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.267495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f650702-cdbb-4804-8b73-96efef81a970 · outbound

This paper cites Buckley, Jason Phang, Samuel R.

Advancing LLM Safe Alignment with Safety Representation Ranking Buckley, Jason Phang, Samuel R

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.771832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c8d59d88-fdb3-48c4-967d-22cefa7f3042 · outbound

This paper cites Contrastive decoding: Open-ended text generation as optimization.

Advancing LLM Safe Alignment with Safety Representation Ranking Contrastive decoding: Open-ended text generation as optimization

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.764757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ac0a7142-37ff-468f-868a-eb0e608aa41a · outbound

This paper cites LiPO: Listwise Preference Optimization through Learning-to-Rank.

Advancing LLM Safe Alignment with Safety Representation Ranking LiPO: Listwise Preference Optimization through Learning-to-Rank

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.276005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c9ed786-fd0b-4fa6-b713-689f1cbdd234 · outbound

This paper cites Jailbreaking chatgpt via prompt engineering: An empirical study, 2023.

Advancing LLM Safe Alignment with Safety Representation Ranking Jailbreaking chatgpt via prompt engineering: An empirical study, 2023

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.756285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 19a89539-8a0e-4f7b-b103-30961419c693 · outbound

This paper cites Harmbench: A standardized evaluation framework for automated red teaming and robust refusal.

Advancing LLM Safe Alignment with Safety Representation Ranking Harmbench: A standardized evaluation framework for automated red teaming and robust refusal

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.748183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 920b1562-7e12-4e7b-bbae-27fc4630439e · outbound

This paper cites Llm improvement for jailbreak defense: Analysis through the lens of over-refusal.

Advancing LLM Safe Alignment with Safety Representation Ranking Llm improvement for jailbreak defense: Analysis through the lens of over-refusal

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.739091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1a4d2249-63e3-4d15-82be-54585b0cc9b8 · outbound

This paper cites Learning to rank from relevance judgments distributions.

Advancing LLM Safe Alignment with Safety Representation Ranking Learning to rank from relevance judgments distributions

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.731853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3880deef-f863-478c-9248-f6abd9dd32cf · outbound

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

Advancing LLM Safe Alignment with Safety Representation Ranking Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.292131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e7fcf81-b543-4765-b4ab-17960c77bb26 · outbound

This paper cites Language models are unsupervised multitask learners.

Advancing LLM Safe Alignment with Safety Representation Ranking Language models are unsupervised multitask learners

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.724627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9fe84c67-cc6c-4ead-b36a-217eec5e76ca · outbound

This paper cites Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning.

Advancing LLM Safe Alignment with Safety Representation Ranking Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.298675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dabb801-295a-4f10-89af-fd05c45770ad · outbound

This paper cites Does Representation Matter? Exploring Intermediate Layers in Large Language Models.

Advancing LLM Safe Alignment with Safety Representation Ranking Does Representation Matter? Exploring Intermediate Layers in Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.301774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a59fc6a-d359-458e-9679-afa9fe96f782 · outbound

This paper cites Reft: Reason- ing with reinforced fine-tuning.

Advancing LLM Safe Alignment with Safety Representation Ranking Reft: Reason- ing with reinforced fine-tuning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.717271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3f10672a-304a-4703-8ad3-1c04084eaa3f · outbound

This paper cites Interpretable prefer- ences via multi-objective reward modeling and mixture-of-experts, 2024.

Advancing LLM Safe Alignment with Safety Representation Ranking Interpretable prefer- ences via multi-objective reward modeling and mixture-of-experts, 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.710402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b13e146a-b522-4359-ae62-890b07fb123d · outbound

This paper cites Self-consistency improves chain of thought reasoning in language models, 2023.

Advancing LLM Safe Alignment with Safety Representation Ranking Self-consistency improves chain of thought reasoning in language models, 2023

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.703409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 76d87c41-7550-4fcb-803c-95150fc61c8c · outbound

This paper cites Chain-of-Thought Reasoning Without Prompting.

Advancing LLM Safe Alignment with Safety Representation Ranking Chain-of-Thought Reasoning Without Prompting

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.315364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01410d90-fb2e-45c3-b15d-3c1fdd2cf1dd · outbound

This paper cites Reinforcement Learning for LLM Post-Training: A Survey.

Advancing LLM Safe Alignment with Safety Representation Ranking Reinforcement Learning for LLM Post-Training: A Survey

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.318170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a62436cd-9a11-4008-8d0f-b9fc08dc48da · outbound

This paper cites Jailbroken: How does llm safety training fail? In NeurIPS, 2023.

Advancing LLM Safe Alignment with Safety Representation Ranking Jailbroken: How does llm safety training fail? In NeurIPS, 2023

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.696723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4ff5d838-7e2d-436e-bfdd-7c848391488d · outbound

This paper cites Assessing the brittleness of safety alignment via pruning and low-rank modifications.

Advancing LLM Safe Alignment with Safety Representation Ranking Assessing the brittleness of safety alignment via pruning and low-rank modifications

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.689585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cba2e2e6-8940-425b-aecc-e698ad06b693 · outbound

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

Advancing LLM Safe Alignment with Safety Representation Ranking Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.326956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb309155-1b6e-4320-9bc9-84c84954840b · outbound

This paper cites Sorry-bench: Systematically evaluating large language model safety refusal.

Advancing LLM Safe Alignment with Safety Representation Ranking Sorry-bench: Systematically evaluating large language model safety refusal

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.680690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3624ce13-2207-4910-9955-e7b32ff13757 · outbound

This paper cites Defending chatgpt against jailbreak attack via self-reminders.

Advancing LLM Safe Alignment with Safety Representation Ranking Defending chatgpt against jailbreak attack via self-reminders

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.673601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation afd28f97-5b04-4eb0-97ef-e529c0821519 · outbound

This paper cites Safedecoding: Defending against jailbreak attacks via safety-aware decoding.

Advancing LLM Safe Alignment with Safety Representation Ranking Safedecoding: Defending against jailbreak attacks via safety-aware decoding

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.665257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation be8921d9-42fc-469f-bbf1-5d22e894abd2 · outbound

This paper cites SafeDecoding: Defending against jailbreak attacks via safety-aware decoding.

Advancing LLM Safe Alignment with Safety Representation Ranking SafeDecoding: Defending against jailbreak attacks via safety-aware decoding

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.657477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f00da5d2-9628-4f22-9a94-712d56489629 · outbound

This paper cites Qwen2.5 Technical Report.

Advancing LLM Safe Alignment with Safety Representation Ranking Qwen2.5 Technical Report

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.340533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4897e823-b2ac-46b6-8d64-cfc0869bffb5 · outbound

This paper cites The ai alignment problem: why it is hard, and where to start.

Advancing LLM Safe Alignment with Safety Representation Ranking The ai alignment problem: why it is hard, and where to start

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.648771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6f8eb0eb-ac04-4593-97d1-5c4917021d8d · outbound

This paper cites Rest-mcts*: Llm self-training via process reward guided tree search, 2024.

Advancing LLM Safe Alignment with Safety Representation Ranking Rest-mcts*: Llm self-training via process reward guided tree search, 2024

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.640308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 512519c3-7e96-443f-9916-7cb34fcf72c8 · outbound

This paper cites Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment.

Advancing LLM Safe Alignment with Safety Representation Ranking Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.352301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11c726b0-6815-4cf2-8850-8ae95c79ce73 · outbound

This paper cites Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models.

Advancing LLM Safe Alignment with Safety Representation Ranking Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.355760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7335f8a0-5cf2-486a-a22c-278fdfb3b4be · outbound

This paper cites Alleviating Hallucinations of Large Language Models through Induced Hallucinations.

Advancing LLM Safe Alignment with Safety Representation Ranking Alleviating Hallucinations of Large Language Models through Induced Hallucinations

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.359366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0399a2e8-9448-474a-bd85-77a28c06a640 · outbound

This paper cites Identifying and tuning safety neurons in large language models.

Advancing LLM Safe Alignment with Safety Representation Ranking Identifying and tuning safety neurons in large language models

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.630684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 135914eb-99a5-4ea8-9117-1f5972336177 · outbound

This paper cites On prompt-driven safeguarding for large language models.

Advancing LLM Safe Alignment with Safety Representation Ranking On prompt-driven safeguarding for large language models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.622074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fc32a28b-3f76-470c-9485-147fba3a9090 · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.

Advancing LLM Safe Alignment with Safety Representation Ranking Judging llm-as-a-judge with mt-bench and chatbot arena

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:18.614468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f6fb1934-e8d9-4420-86c5-a02c5fbc6c9d · outbound

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

Advancing LLM Safe Alignment with Safety Representation Ranking Representation Engineering: A Top-Down Approach to AI Transparency

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.372422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f6565bc-a792-400e-bdc0-4283ea8e43e1 · outbound

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

Advancing LLM Safe Alignment with Safety Representation Ranking Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:18.375972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 68fbd259-3bde-4437-be77-bca5152543d5 · inbound

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction cites this paper.

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction Advancing LLM Safe Alignment with Safety Representation Ranking

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-19T11:37:15.979737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c7dca5b9-3fc8-4cb6-8db9-aa8408d99216 · inbound

SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems cites this paper.

SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems Advancing LLM Safe Alignment with Safety Representation Ranking

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T18:28:42.361096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a53ea7aa-a633-4276-a61b-37f552736f54 · inbound

RACC: Representation-Aware Coverage Criteria for LLM Safety Testing cites this paper.

RACC: Representation-Aware Coverage Criteria for LLM Safety Testing Advancing LLM Safe Alignment with Safety Representation Ranking

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:17:36.595720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a4b926b3-8045-41df-b52e-6a8e2d99b298 · inbound

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models cites this paper.

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models Advancing LLM Safe Alignment with Safety Representation Ranking

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:20:57.877835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 89529674-b1c6-4487-b39e-fb4ea1fe192f · inbound

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models cites this paper.

Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models Advancing LLM Safe Alignment with Safety Representation Ranking

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T16:34:03.109901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 699e43b1-d54f-4e87-8814-1f71419681ee · inbound

Enabling Performant and Flexible Model-Internal Observability for LLM Inference cites this paper.

Enabling Performant and Flexible Model-Internal Observability for LLM Inference Advancing LLM Safe Alignment with Safety Representation Ranking

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-13T07:17:28.099483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0052c1e3-00a1-45f5-815f-da6460ec14ae · inbound

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion cites this paper.

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion Advancing LLM Safe Alignment with Safety Representation Ranking

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:57:06.438225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5a07c4bf-19c0-4db0-8171-0a934fd3a2c8 · inbound

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion cites this paper.

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion Advancing LLM Safe Alignment with Safety Representation Ranking

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:12:58.890972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5804f189-3924-43bc-8d23-1def0dfe31b8 · inbound

A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle cites this paper.

A Distributional View for Visual Mechanistic Interpretability: KL-Minimal Soft-Constraint Principle Advancing LLM Safe Alignment with Safety Representation Ranking

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:58:20.492100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 26572c6e-29ee-4df8-8692-090764d1656b · inbound

Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures cites this paper.

Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures Advancing LLM Safe Alignment with Safety Representation Ranking

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-06-29T07:53:14.434543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cd001eb1-32a0-4b4e-8862-f544de839176 · inbound

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs cites this paper.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Advancing LLM Safe Alignment with Safety Representation Ranking

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-31T23:07:40.652133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.