Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-10T16:00:32.413225Z
Paper Citation Record · LEDGER
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
As of 12 August 2026, this Paper Citation Record lists 77 of 77 outbound references and 7 inbound Pith citation observations for arXiv:2605.01687.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-06T00:32:05.121298Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-04T17:09:59.507308Z
Reference resolution
77 of 77 outbound references displayed
- verified exact7
- verified fuzzy44
- unresolved1
- parse uncertain0
- malformed identifier0
- metadata mismatch25
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 6fdd3147-9efa-4984-86a8-9b384510be0f · outbound
This paper cites 2025 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , eprint=
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.523408Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 676444c2-0a0b-4f5f-9d8d-2ca95f458ef9 · outbound
This paper cites 2025 , institution =.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , institution =
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.584202Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation b3b87e30-6c09-446a-a728-ee5dc5783903 · outbound
This paper cites 2025 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , eprint=
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.556000Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 93ac462f-cbda-41d9-8f5b-c8f90a108bcf · outbound
This paper cites 34th USENIX Security Symposium (USENIX Security 25) , pages=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 34th USENIX Security Symposium (USENIX Security 25) , pages=
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.472746Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 564491a8-4c05-4997-9103-3bee6e9e20a3 · outbound
This paper cites LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
Reference 5
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:01.117969Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 2802c7a5-7496-43c9-8516-3cc02f1f917a · outbound
This paper cites RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking
Reference 6
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:01.171116Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation a88475d0-e077-4036-9211-16f51b5852f3 · outbound
This paper cites SafeDialBench: A Fine-Grained Safety Benchmark for Large Language Models in Multi-Turn Dialogues.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety SafeDialBench: A Fine-Grained Safety Benchmark for Large Language Models in Multi-Turn Dialogues
Reference 7
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:01.061328Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation ccc0fa3b-dfe9-4e8b-b4b9-e7df34205fd6 · outbound
This paper cites Safety Alignment Should Be Made More Than Just a Few Tokens Deep.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Safety Alignment Should Be Made More Than Just a Few Tokens Deep
Reference 8
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:00.975345Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 0fc7078f-aac2-4fd6-a0f5-f2d1a84b7cb4 · outbound
This paper cites Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T09:31:01.194142Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 594b6990-04dc-4f50-a459-fa24738536e2 · outbound
This paper cites CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T09:31:01.152129Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 6d6b49f1-708a-4c48-8980-89990592fc73 · outbound
This paper cites 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) , pages=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) , pages=
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.479664Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 159f575c-bfda-4c4a-9682-b2616b6b7fd1 · outbound
This paper cites 2023 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2023 , eprint=
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.568138Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 0d7deb2d-7458-48cc-b837-dabc224129f4 · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Advances in Neural Information Processing Systems , volume=
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.527230Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation ec801bc7-02f6-4cd4-b697-fc8ec09f7a77 · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Advances in Neural Information Processing Systems , volume=
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.588249Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 7ed6d5f1-d36b-4169-a314-f39385239b51 · outbound
This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Reference 15
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T09:31:01.259730Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 2757514c-1a43-4899-8217-206f5c486cfe · outbound
This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 16
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T09:31:01.090545Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 6a9c689d-4263-40dd-a3d4-7dd306a4c755 · outbound
This paper cites SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T09:31:00.988350Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 8e386a28-aaa2-4d51-9187-1f729c03705b · outbound
This paper cites Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
Reference 18
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:01.284910Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 3b2fab11-c5ea-4daf-85e9-6c5c0e388825 · outbound
This paper cites JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
Reference 19
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:01.031176Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 67893cbf-c80c-41c7-b2d2-f3776cc73794 · outbound
This paper cites Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs
Reference 20
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:01.138639Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 5cc4aa8d-625b-4899-89a0-bb40273b0134 · outbound
This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
Reference 21
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T08:58:35.940011Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation a302b4f9-a0ef-419f-af3f-5b3279fb3f1e · outbound
This paper cites Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
Reference 22
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-16T22:00:51.596826Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 8bbcf1f9-cc39-4b84-866b-3b1ee981fff3 · outbound
This paper cites Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models
Reference 23
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:01.017286Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 4f3c832a-db8e-4de2-8d4b-61621425defc · outbound
This paper cites 2024 , eprint =.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2024 , eprint =
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.509657Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation dd350fd1-a586-4b59-b169-dcc003e615ff · outbound
This paper cites Computer , volume=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Computer , volume=
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.562450Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 83f0276c-0ad2-4226-a085-e9664158827c · outbound
This paper cites 2025 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , eprint=
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.616996Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation e381182a-4d43-467b-8942-e565a580950e · outbound
This paper cites 2025 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , eprint=
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.591576Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 2b16e8d8-2266-476f-80e7-353915615796 · outbound
This paper cites 2025 , month = apr, day =.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , month = apr, day =
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.553241Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 5aaa337b-cf50-42b5-ae66-09c6cf565524 · outbound
This paper cites Best-of-N Jailbreaking.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Best-of-N Jailbreaking
Reference 29
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:01.204907Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation e459db5c-d7c9-402f-b794-eb4824565c12 · outbound
This paper cites 2025 , month = feb, day =.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , month = feb, day =
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.512822Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 16b7f8c6-a63b-4aaa-84e3-3a9c9df98daa · outbound
This paper cites Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Reference 31
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T09:31:01.210573Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 75b0a355-faa2-430b-b9f8-462641cb5333 · outbound
This paper cites author=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety author=
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.559341Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 095f2c12-a894-4ffa-94d0-3f81ba387840 · outbound
This paper cites 2024 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2024 , eprint=
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.609051Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 58db8de2-4657-4f0c-b486-b091a2229339 · outbound
This paper cites From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models
Reference 34
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:00.953629Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation e467c562-5fe0-4b1d-827d-bd917a361b38 · outbound
This paper cites 2024 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2024 , eprint=
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.597853Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 9b175977-93f9-46c1-aecf-86bc36f4500f · outbound
This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Reference 36
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T09:31:01.181661Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation cf6f2377-d72e-441c-a573-7eeb4dc16afa · outbound
This paper cites GPT-4o System Card.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety GPT-4o System Card
Reference 37
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T09:31:01.291137Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 81b4e7d8-23c5-4eb3-a577-99832bf8482a · outbound
This paper cites MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue
Reference 38
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:01.003678Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 37728d1d-6f66-4029-9283-10849ec654a8 · outbound
This paper cites Advances in Neural Information Processing Systems , volume=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Advances in Neural Information Processing Systems , volume=
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.577233Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation bdf4ee67-6c63-4b44-a0e6-ce72407fe6bb · outbound
This paper cites 2025 , howpublished =.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , howpublished =
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.547881Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 381e3394-bafc-422c-ab49-97921b793512 · outbound
This paper cites 2024 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2024 , eprint=
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.581206Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 7210aaf0-1365-44fa-b328-d94281f84e69 · outbound
This paper cites SoSBench: Benchmarking Safety Alignment on Six Scientific Domains.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
Reference 42
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T09:31:01.236234Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 4279a036-820a-4619-8e3f-e68edefdcb15 · outbound
This paper cites SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
Reference 43
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:01.221364Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 8d8d3568-fe6a-4bdb-a3be-123e29301775 · outbound
This paper cites IEEE Transactions on Neural Networks and Learning Systems , volume=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety IEEE Transactions on Neural Networks and Learning Systems , volume=
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.485941Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation d173da48-cc9b-478c-beb5-18c13f963ae6 · outbound
This paper cites On Statistical Bias In Active Learning: How and When To Fix It.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety On Statistical Bias In Active Learning: How and When To Fix It
Reference 45
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T09:31:01.009039Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation b809b336-e4db-44ff-922c-99944a7e300d · outbound
This paper cites Self-Taught Evaluators.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Self-Taught Evaluators
Reference 46
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:01.129656Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 5e7bdbf8-685c-4fc0-8c81-62c31d660c87 · outbound
This paper cites 2024 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2024 , eprint=
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.482653Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 37bdac1c-5d68-433f-b4cc-e622b3ea3d5a · outbound
This paper cites 2024 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2024 , eprint=
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.516652Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 2c98548d-9303-4178-8206-d60e67cb8f48 · outbound
This paper cites 2025 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , eprint=
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.542339Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation ac8858e5-a760-4fc8-94b8-9168e07f01ec · outbound
This paper cites Standard Models , author=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Standard Models , author=
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.539508Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 0f7faae3-cd8f-4371-9f6b-0608d11dea79 · outbound
This paper cites 2025 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , eprint=
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.492226Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 358e08b6-e893-47d9-9bb2-f82c6c91c74f · outbound
This paper cites 2023 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2023 , eprint=
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.489172Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 2df1776f-2fd1-4471-819d-998a7098d14f · outbound
This paper cites 2024 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2024 , eprint=
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.536562Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 885bfa4b-ea8a-4a04-81a8-751462a3e0fc · outbound
This paper cites Continuous Judgment Tasks , author=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Continuous Judgment Tasks , author=
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.602041Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 858fa60d-121f-4e21-b07b-976acde966e2 · outbound
This paper cites 2024 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2024 , eprint=
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.545173Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 7ac2853b-77b7-4c43-b562-1fdf5c0d71a5 · outbound
This paper cites 2025 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , eprint=
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.530100Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 335ec422-e60e-4221-b583-cddfc5eae1c8 · outbound
This paper cites 2025 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , eprint=
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.498805Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 134c2e54-2d36-4e10-9bad-97879483cc8c · outbound
This paper cites 2025 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , eprint=
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.502712Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation d472260b-92f9-4496-8d5b-13acd40cad6c · outbound
This paper cites 2025 , url =.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , url =
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.533135Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 8d8e083d-a766-49e0-bd6b-d980fc77c9da · outbound
This paper cites 2024 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2024 , eprint=
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.613001Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 346158e7-c21e-4343-92e1-3b5246e5ebc9 · outbound
This paper cites 2024 , url =.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2024 , url =
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.550605Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation fcc5ba13-c697-44ff-adba-f3fc6cf884e4 · outbound
This paper cites 2023 , howpublished =.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2023 , howpublished =
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.565358Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 2f294101-b005-4cdd-b3ea-149c0c3dc72d · outbound
This paper cites 2025 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2025 , eprint=
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.574362Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 14468d95-2a9d-4946-8b71-0bd01fc3ecb4 · outbound
This paper cites 2023 , eprint=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2023 , eprint=
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.620546Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation b23637f1-ef7d-4a3c-a06f-cfd6d7aa7bcc · outbound
This paper cites Advances in neural information processing systems , volume=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Advances in neural information processing systems , volume=
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.571482Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 06be3a5d-de18-4a8c-abfd-6c8757d6969e · outbound
This paper cites Educ Psychol Meas , volume=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Educ Psychol Meas , volume=
Reference 66
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.605630Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 8eadd351-68b8-4279-bc13-23c1a31946e5 · outbound
This paper cites & Shao, J.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety & Shao, J
Reference 67
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:01.052993Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 30079e97-6687-405e-b831-e22a2b7b2820 · outbound
This paper cites Steering dialogue dynamics for robust- ness against multi-turn jailbreaking attacks.arXiv preprint arXiv:2503.00187.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Steering dialogue dynamics for robust- ness against multi-turn jailbreaking attacks.arXiv preprint arXiv:2503.00187
Reference 68
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T09:31:01.073795Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 2bf7f2eb-20c9-4b4a-8778-8363e4058464 · outbound
This paper cites X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
Reference 69
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T09:31:01.098291Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation d5ab5270-0b75-4bc3-8b4a-e7016fd8327e · outbound
This paper cites 2026 , publisher=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2026 , publisher=
Reference 70
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.594614Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation dff50217-3abb-4fc2-b9dc-b41f6d626a53 · outbound
This paper cites an unresolved cited work.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Unresolved cited work
Reference 71
- Resolution
- unresolved
- raw_fallback, observed 2026-05-17T17:25:00.519929Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation e7c8572c-03e7-4f97-8a32-de928a2428ea · outbound
This paper cites 2019 IEEE symposium on security and privacy (SP) , pages=.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2019 IEEE symposium on security and privacy (SP) , pages=
Reference 72
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.476028Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 8f69c2c3-9436-4e3c-8481-401af6484992 · outbound
This paper cites A Repository of Conversational Datasets.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety A Repository of Conversational Datasets
Reference 73
- Resolution
- verified exact
- arxiv_id, observed 2026-07-04T23:40:06.189886Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 91f98b2d-f620-4f93-98d4-8a539eddfc09 · outbound
This paper cites gpt-oss-120b & gpt-oss-20b Model Card.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety gpt-oss-120b & gpt-oss-20b Model Card
Reference 74
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T09:31:01.107243Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 741ebe01-1101-4823-9dcf-8eb789514f8f · outbound
This paper cites Qwen3Guard Technical Report.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Qwen3Guard Technical Report
Reference 75
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T22:33:37.835217Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 42caccb8-ce6d-4cb4-8c1b-9219d9579b58 · outbound
This paper cites Sema: Simple yet effective learning for multi-turn jailbreak attacks.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety Sema: Simple yet effective learning for multi-turn jailbreak attacks
Reference 76
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T09:31:01.043904Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 280d419c-2947-4a17-a985-2c2a8e3ae704 · outbound
This paper cites 2026 , eprint =.
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety 2026 , eprint =
Reference 77
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T17:25:00.505825Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Pith citing papers
Observation f2a19d41-325d-4348-a32c-b929caee1f59 · inbound
Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models cites this paper.
Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
Reference 36
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T17:53:47.689060Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation de24e602-c619-4b58-a1f9-261f2b923446 · inbound
NRT-Bench: Benchmarking Multi-Turn Red-Teaming of LLM Operator Agents in Safety-Critical Control Rooms cites this paper.
NRT-Bench: Benchmarking Multi-Turn Red-Teaming of LLM Operator Agents in Safety-Critical Control Rooms MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
Reference 20
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T04:09:34.509121Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 68e46dcc-a896-4433-b543-912a1afd7275 · inbound
PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models cites this paper.
PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-07-04T17:09:59.508529Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation e3ad3acc-b288-4b6b-97c0-81ab76f9625d · inbound
EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures cites this paper.
EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T06:24:18.533375Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation f2ad8565-af09-4cf7-ad3e-6b31b461f799 · inbound
EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures cites this paper.
EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
Reference 9471
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T09:38:57.860575Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b558507a-d528-437b-935f-a181025123af · inbound
EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures cites this paper.
EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
Reference 9471
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T02:07:27.996765Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 873285c7-9390-4192-b59f-e258f18a6098 · inbound
SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks cites this paper.
SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
Reference 96
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T00:32:05.121298Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.