Paper Citation Record · LEDGER

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement

As of 20 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2505.12060.

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

pith.paper-citation-record.v1
2505.12060 v1

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:45:55.362359Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

47 of 47 outbound references displayed

verified exact0
verified fuzzy2
unresolved45
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5f5ca2fb-bb12-474c-ac85-7b04b62ded77 · outbound

This paper cites online" 'onlinestring :=.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.159478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b3634ff-3a7f-4799-831b-b9a59b111d77 · outbound

This paper cites write newline.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.164792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0b12999-6932-43f8-b9ce-e7d29cc44176 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Detecting Language Model Attacks with Perplexity

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.174359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cd3e906-c155-48d7-a3c5-abfe4e6e4ba3 · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.178874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21f0dac6-028c-4fa4-8fe6-48587e7016a1 · outbound

This paper cites Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.183166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0bd4047-d1a1-4601-8414-9f581ac26c13 · outbound

This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.188436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f548a7b-3fc5-4eac-9ff3-3dedfacf0622 · outbound

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

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.193949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c3988a0-6d84-435c-9019-45aa0021fcf2 · outbound

This paper cites Christiano, Jan Leike, Tom B.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Christiano, Jan Leike, Tom B

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.199906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85a10d4a-ed63-4aa5-937e-582dc1ceeede · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Training Verifiers to Solve Math Word Problems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.204727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41ae1dcd-99fb-4380-b91e-9b055704f53e · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.209718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f94cd4ae-7843-4f5f-b1cb-2dccc3688720 · outbound

This paper cites Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.214729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9db4da0b-733e-4971-a04f-ca46c8ffe92f · outbound

This paper cites The Llama 3 Herd of Models.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement The Llama 3 Herd of Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.219549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00ce8e54-3942-40b9-bb4d-fdd9659524cf · outbound

This paper cites The Ethics of Advanced AI Assistants.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement The Ethics of Advanced AI Assistants

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.223921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5e70198-796f-40b0-b3e4-dd8c3fb3dfc5 · outbound

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

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.228774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a67fc54-b43f-43c3-a5b4-b11b99e9e51e · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Measuring Massive Multitask Language Understanding

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.233816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24369157-fdf1-4369-9ea4-7edcf20d8af4 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.237655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b96e56c8-99b4-4f6f-919d-da1aebb16906 · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.241736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d314247-71de-421a-9805-f6aa364a32b3 · outbound

This paper cites Buckley, Jason Phang, Samuel R.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Buckley, Jason Phang, Samuel R

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:45:55.845907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 051b2a5a-2b35-45c1-8767-fa7a6da36ecd · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.249621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4d2ec25-105a-494a-b06d-c3993c108f27 · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.253570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76963d67-9297-4349-8e49-f749002a0979 · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:45:55.826768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 27c125a0-efac-4f97-aca5-bd1986b51276 · outbound

This paper cites Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.261508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 689c87a8-a493-457f-a151-30b5f9fab1dc · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.265548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 226b1c8b-c92b-4e19-a3a8-a5a52ad963c8 · outbound

This paper cites GPT-4 Technical Report.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement GPT-4 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.269328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8338340-6c13-4c01-9fe8-0cd385686949 · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:45:55.805968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a8464431-916f-4204-8d0d-7c8d97e59d59 · outbound

This paper cites LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.276673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9820e6e7-89f9-41bb-8760-54975fc5fc25 · outbound

This paper cites Qwen2.5 Technical Report.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Qwen2.5 Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.281083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4a222ed-31f7-49ee-8ec7-1168988832d5 · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.284916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 664885f0-8c54-405a-994f-33af0ee3186e · outbound

This paper cites do anything now.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement do anything now

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:45:55.791478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 97929627-fe81-4ea4-bc8b-701da48999f6 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Gemma 2: Improving Open Language Models at a Practical Size

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.293139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de251238-8b88-4a7d-a869-d2776c500b30 · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.296693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eb52288-476f-4e6d-b3fd-d833ec2325f7 · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:45:55.772534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 505700fc-08fe-42b2-868a-0df040fe0d5e · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:45:55.760377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 97e70e77-2b67-495b-9d54-d0d2e56fccd6 · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.307537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2908be1-0bdb-4385-8425-46098b195243 · outbound

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

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.311556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95a3d297-22ff-4cde-b225-c4f24ce8a503 · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:45:55.748379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c226f6fc-d887-4cdf-826e-39b600e10ddf · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.319351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bffd855d-015d-46e8-9e16-cfe41e746466 · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.323905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83de0397-68ad-4fbd-b876-9211e302c92a · outbound

This paper cites How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.328199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e7eaa9f-2b88-4bdc-afa5-949f2daba906 · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:45:55.736800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 410697ab-5fa0-4466-a3c3-715ecfe5905b · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:45:55.723373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c72befb0-ed0d-48e0-9948-e8042d70e250 · outbound

This paper cites Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.339667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6c1b6c0-72f5-4802-b42b-09673dcd3c4a · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:45:55.711455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0b270832-d925-4afe-950e-90d540832e67 · outbound

This paper cites How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.350773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b4ea130-3938-4c43-89fc-9d0bc8f5936b · outbound

This paper cites an unresolved cited work.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:45:55.697533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 661e75be-95a1-4712-9f48-5c72250d2c3c · outbound

This paper cites Can Large Language Models Understand Context?.

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Can Large Language Models Understand Context?

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.358524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f86432d-de1c-4f80-95a9-30a9affc5135 · outbound

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

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T20:45:55.362359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.