Paper Citation Record · LEDGER

Mitigating Jailbreaks with Intent-Aware LLMs

As of 22 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 1 inbound Pith citation observation for arXiv:2508.12072.

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

pith.paper-citation-record.v1
2508.12072 v2

Coverage vector

measured 56 of 56 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:29:10.244362Z

measured 57 of 57 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-08T10:00:02.677030Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-08T10:04:51.400037Z

Reference resolution

56 of 56 outbound references displayed

verified exact0
verified fuzzy11
unresolved45
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3c47d5bc-078a-4911-9100-e4c7d9d32834 · outbound

This paper cites Jailbreaking leading safety-aligned LLM s with simple adaptive attacks.

Mitigating Jailbreaks with Intent-Aware LLMs Jailbreaking leading safety-aligned LLM s with simple adaptive attacks

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:29:11.506187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ff32cf5d-a269-441e-a9f2-ea87259c1f43 · outbound

This paper cites Activating ai safety level 3 protections.

Mitigating Jailbreaks with Intent-Aware LLMs Activating ai safety level 3 protections

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:29:11.485732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0b033b50-671b-46d4-81b7-46f84c169124 · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs Refusal in language models is mediated by a single direction

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:29:11.466366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ef4bdce6-965c-4458-a52e-d6b2ddea170e · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

Mitigating Jailbreaks with Intent-Aware LLMs A General Language Assistant as a Laboratory for Alignment

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.902399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ad2a0fb-09d3-4301-b1c6-f2b2ac4e7ff3 · outbound

This paper cites GASP : Efficient black-box generation of adversarial suffixes for jailbreaking LLM s.

Mitigating Jailbreaks with Intent-Aware LLMs GASP : Efficient black-box generation of adversarial suffixes for jailbreaking LLM s

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:29:11.446110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 59b184fa-1d4b-4f0d-ada9-f989831c3c4f · outbound

This paper cites Safety-tuned LL a MA s: Lessons from improving the safety of large language models that follow instructions.

Mitigating Jailbreaks with Intent-Aware LLMs Safety-tuned LL a MA s: Lessons from improving the safety of large language models that follow instructions

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.913375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a1a998c-30b8-42e9-b002-bd04ea3bd9c6 · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.919474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8bfb122-33d5-4986-b14c-174550b222c9 · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.925144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f0dd45f-00fa-4e13-a78b-cadf03b6f165 · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs Jailbreaking black box large language models in twenty queries

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.930800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63de3034-a7a0-40ac-a943-b50d34b6a3f0 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Mitigating Jailbreaks with Intent-Aware LLMs Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.936340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13d2f2a6-8ea2-4f8a-9396-3cf5042ee6f6 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Mitigating Jailbreaks with Intent-Aware LLMs Training Verifiers to Solve Math Word Problems

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.943941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3be2c77-c0f2-4937-92bf-84b0262b70b6 · outbound

This paper cites A mathematical framework for transformer circuits.

Mitigating Jailbreaks with Intent-Aware LLMs A mathematical framework for transformer circuits

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.952336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f26b293-9976-48dd-8802-4f36cffd17f4 · outbound

This paper cites The Llama 3 Herd of Models.

Mitigating Jailbreaks with Intent-Aware LLMs The Llama 3 Herd of Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.958673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 021d5cfe-93c4-4e14-9fa0-793148835295 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Mitigating Jailbreaks with Intent-Aware LLMs Measuring Massive Multitask Language Understanding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.965838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0edbdc2-8b21-4269-b1c7-949d6e369a13 · outbound

This paper cites Intention awareness: Improving upon situation awareness in human-centric environments.

Mitigating Jailbreaks with Intent-Aware LLMs Intention awareness: Improving upon situation awareness in human-centric environments

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:29:11.391025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 853b76b3-30c6-4bd7-bd76-5bbaadc4f97c · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.980047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6234d0f2-dcd9-42b5-af94-bb3c41225c08 · outbound

This paper cites Mixtral of Experts.

Mitigating Jailbreaks with Intent-Aware LLMs Mixtral of Experts

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.986599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc856a12-6e8b-41d8-8f0f-b6485dbe3ec4 · outbound

This paper cites Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models.

Mitigating Jailbreaks with Intent-Aware LLMs Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.992450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44f10ae0-5251-4bde-885a-99f4a207a0b8 · outbound

This paper cites The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning.

Mitigating Jailbreaks with Intent-Aware LLMs The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:09.999175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22c555b8-c51d-479d-97ad-bac6f2b5d7b8 · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.005464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54677ca1-7d48-4193-af87-dd22cd5eee36 · outbound

This paper cites DeepSeek-V3 Technical Report.

Mitigating Jailbreaks with Intent-Aware LLMs DeepSeek-V3 Technical Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.012108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5338bdcf-806b-413c-a126-cec8fac44fe9 · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

Mitigating Jailbreaks with Intent-Aware LLMs AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.019491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e860e02-3f08-4eee-8f69-55d3dc824a19 · outbound

This paper cites PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails.

Mitigating Jailbreaks with Intent-Aware LLMs PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.029145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 403c4415-1430-4150-8002-1e9843f09e9d · outbound

This paper cites GPTEval : A survey on assessments of ChatGPT and GPT-4.

Mitigating Jailbreaks with Intent-Aware LLMs GPTEval : A survey on assessments of ChatGPT and GPT-4

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:29:11.362490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3ae14a51-dbc4-42b3-90f1-e23a9b1669bf · outbound

This paper cites Interpreting GPT : The logit lens, 2020.

Mitigating Jailbreaks with Intent-Aware LLMs Interpreting GPT : The logit lens, 2020

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:29:11.343169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 03e33d49-f9a8-4592-8c47-fae210e467a2 · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs Training language models to follow instructions with human feedback

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.047010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb54500f-058f-4482-bdc6-9d96135326db · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Mitigating Jailbreaks with Intent-Aware LLMs Steering Llama 2 via Contrastive Activation Addition

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.052229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a225055-0953-4e84-b4e3-ed03311b145e · outbound

This paper cites Rapid Response: Mitigating LLM Jailbreaks with a Few Examples.

Mitigating Jailbreaks with Intent-Aware LLMs Rapid Response: Mitigating LLM Jailbreaks with a Few Examples

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.059063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1967755b-1600-452e-a007-171c105495d1 · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.065531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 363cc3c7-c03e-409c-b430-ade50ee50753 · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.071729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95a18e53-130b-4ffa-9d6b-9ba0555f5520 · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs Direct preference optimization: Your language model is secretly a reward model

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.078388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e43708b6-0e92-475d-99dc-534bc8a2f176 · outbound

This paper cites Gpqa: A graduate-level google-proof q&a benchmark.

Mitigating Jailbreaks with Intent-Aware LLMs Gpqa: A graduate-level google-proof q&a benchmark

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.083742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e191eec-8cc5-42bf-866f-9dc69522eafc · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.089503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 916aba2d-6834-429c-a140-da9de1f01423 · outbound

This paper cites XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.

Mitigating Jailbreaks with Intent-Aware LLMs XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.096105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75bf6229-c3f8-4972-b8ad-3cf180975230 · outbound

This paper cites A trivial jailbreak against llama 3.

Mitigating Jailbreaks with Intent-Aware LLMs A trivial jailbreak against llama 3

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:29:11.284859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b30ac8b4-1fdd-4b70-ae18-d0e80df57d38 · outbound

This paper cites Hashimoto.

Mitigating Jailbreaks with Intent-Aware LLMs Hashimoto

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.109488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8137613-46a6-4763-b7e6-b6edb5f68863 · outbound

This paper cites Steering Language Models With Activation Engineering.

Mitigating Jailbreaks with Intent-Aware LLMs Steering Language Models With Activation Engineering

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.115243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f42bf46-0ab5-442e-8e3e-686ad93b263d · outbound

This paper cites Attention is all you need.

Mitigating Jailbreaks with Intent-Aware LLMs Attention is all you need

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.121110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e08b5517-3148-4184-8c94-4806f4113af1 · outbound

This paper cites Backdooralign: Mitigating fine-tuning based jailbreak attack with backdoor enhanced safety alignment.

Mitigating Jailbreaks with Intent-Aware LLMs Backdooralign: Mitigating fine-tuning based jailbreak attack with backdoor enhanced safety alignment

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:29:11.238788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f1670cfe-f217-4d1b-a61c-5d69e4ad09a0 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Mitigating Jailbreaks with Intent-Aware LLMs Chain-of-thought prompting elicits reasoning in large language models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.132535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9443b52e-49d8-4b5e-b54b-912e938cb6bd · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.137872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7396fc9-14c9-4ac8-bf22-f3fa6ae7041f · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs Defending chatgpt against jailbreak attack via self-reminders

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.143425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 008c067d-6be2-406a-86c9-b962e2d64528 · outbound

This paper cites an unresolved cited work.

Mitigating Jailbreaks with Intent-Aware LLMs Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-15T17:29:11.197462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6bb7a1ac-0db6-4658-973b-29e124550a31 · outbound

This paper cites Qwen3 Technical Report.

Mitigating Jailbreaks with Intent-Aware LLMs Qwen3 Technical Report

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.155747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21c0f68c-05f5-45de-8f2d-d8090664d7ac · outbound

This paper cites Understanding Refusal in Language Models with Sparse Autoencoders.

Mitigating Jailbreaks with Intent-Aware LLMs Understanding Refusal in Language Models with Sparse Autoencoders

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.162261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0dae1fc-7da4-42d3-9976-ed7b99e495be · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

Mitigating Jailbreaks with Intent-Aware LLMs GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.169290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdaec08b-c9ea-489f-ba3f-ef2362598c0c · outbound

This paper cites How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms.

Mitigating Jailbreaks with Intent-Aware LLMs How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:29:11.173330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f8370a41-0248-4bd0-9d69-30bf64fb40aa · outbound

This paper cites Intention Analysis Makes LLMs A Good Jailbreak Defender.

Mitigating Jailbreaks with Intent-Aware LLMs Intention Analysis Makes LLMs A Good Jailbreak Defender

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.184512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91f1dd1e-2f8b-4c24-9cdc-9b38a1ce7133 · outbound

This paper cites 1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training.

Mitigating Jailbreaks with Intent-Aware LLMs 1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.191260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 876c3381-9c27-4c56-a3c4-0a13060e8389 · outbound

This paper cites Improved few-shot jailbreaking can circumvent aligned language models and their defenses.

Mitigating Jailbreaks with Intent-Aware LLMs Improved few-shot jailbreaking can circumvent aligned language models and their defenses

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:29:11.151312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5d9f8eab-517e-4fd1-a044-4dd506347ec6 · outbound

This paper cites Reasoning-to-defend: Safety-aware reasoning can defend large language models from jailbreaking.

Mitigating Jailbreaks with Intent-Aware LLMs Reasoning-to-defend: Safety-aware reasoning can defend large language models from jailbreaking

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.203834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca6244fc-8205-4bb5-9524-e97f91c234ba · outbound

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

Mitigating Jailbreaks with Intent-Aware LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.214076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e39e89d7-4539-43eb-8341-579ba0114310 · outbound

This paper cites write newline.

Mitigating Jailbreaks with Intent-Aware LLMs write newline

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.220344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42bf9968-7716-4cf6-bdbe-b604aa7e73a0 · outbound

This paper cites @esa (Ref.

Mitigating Jailbreaks with Intent-Aware LLMs @esa (Ref

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.228790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8055015f-f9de-4743-8421-f05ec6aa6590 · outbound

This paper cites an unresolved cited work.

Mitigating Jailbreaks with Intent-Aware LLMs Unresolved cited work

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.237302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccfee3f8-9b7d-4227-afdb-a4b12c04e79c · outbound

This paper cites an unresolved cited work.

Mitigating Jailbreaks with Intent-Aware LLMs Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T17:29:10.244362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 89d30831-1b5d-4210-8782-5bdf095841ab · inbound

DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail cites this paper.

DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail Mitigating Jailbreaks with Intent-Aware LLMs

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-08T10:04:51.403792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.