Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-18T21:34:51.665401Z
Paper Citation Record · LEDGER
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs
As of 6 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 1 inbound Pith citation observation for arXiv:2508.20325.
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 2026-08-05T06:32:48.257954+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-05-10T16:05:09.033412Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-05-11T09:21:00.875633Z
Reference resolution
61 of 61 outbound references displayed
- verified exact10
- verified fuzzy21
- unresolved7
- parse uncertain0
- malformed identifier1
- metadata mismatch22
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 9f9d800a-8f84-435a-a63d-65f7e40f39df · outbound
This paper cites Journal of experimental political science 9(1), 104–117 (2022).
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Journal of experimental political science 9(1), 104–117 (2022)
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.510498Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 17c02676-cb49-44b3-9322-6652d95bacfc · outbound
This paper cites Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations
Reference 2
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T21:36:52.538697Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b6e80b81-4dcd-4456-8b7d-eb0beca2dcf9 · outbound
This paper cites Computer Law Review International 20(4), 97–106 (2019) 14.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Computer Law Review International 20(4), 97–106 (2019) 14
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.507524Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 617d0056-91d9-4b76-b5a3-4e7f565a3e5b · outbound
This paper cites https:// www.aepd.es/sites/default/files/2019-12/ai-ethics-guidelines.pdf.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs https:// www.aepd.es/sites/default/files/2019-12/ai-ethics-guidelines.pdf
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.520473Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 36a52f62-46d2-4e14-b124-ab9ce795e576 · outbound
This paper cites "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
Reference 5
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T21:36:52.543549Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation c96c01fc-a47a-49e4-a28e-f55a81956a11 · outbound
This paper cites Retrieved August 24, 2018 (2016).
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Retrieved August 24, 2018 (2016)
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.501505Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation fd47df4b-6d1b-40c3-b1fd-7424c6a93547 · outbound
This paper cites https://www.whitehouse.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs https://www.whitehouse
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.513184Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation dd16909e-5b76-4ffa-84f8-68abfe4b6a1c · outbound
This paper cites https: //www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/ executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs https: //www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/ executive-order-on-the-safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence/
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.504555Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 6753390a-b2c7-48c6-90a3-c457f2451d9e · outbound
This paper cites https://www.nist.gov/itl/ai-risk-management-framework.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs https://www.nist.gov/itl/ai-risk-management-framework
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.516573Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 3af16540-817b-4bf9-b7e9-95e2647b4e4c · outbound
This paper cites https:// assets.publishing.service.gov.uk/media/64cb71a547915a00142a91c4/ a-pro-innovation-approach-to-ai-regulation-amended-web-ready.pdf.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs https:// assets.publishing.service.gov.uk/media/64cb71a547915a00142a91c4/ a-pro-innovation-approach-to-ai-regulation-amended-web-ready.pdf
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.524524Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation dc8c2dad-3780-4218-b9d1-d4dbaed9545b · outbound
This paper cites https://artificialintelligenceact.eu/ ai-act-explorer/.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs https://artificialintelligenceact.eu/ ai-act-explorer/
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.529510Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d3255833-f4a6-456b-8cee-eea0a074bc9e · outbound
This paper cites ChatDev: Communicative Agents for Software Development.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs ChatDev: Communicative Agents for Software Development
Reference 12
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T21:36:52.430664Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 0f8952ac-551d-4905-889c-920b7e5bc657 · outbound
This paper cites MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
Reference 13
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T21:36:52.388845Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d9da99c8-fa42-40dc-9037-86276faca79b · outbound
This paper cites Voyager: An Open-Ended Embodied Agent with Large Language Models.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Voyager: An Open-Ended Embodied Agent with Large Language Models
Reference 14
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T21:36:52.379499Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b54939ce-00ce-420e-87cd-32ade625a2bb · outbound
This paper cites In: Proceedings of the 36th Annual Acm Symposium on User Interface Software and Technology, pp.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs In: Proceedings of the 36th Annual Acm Symposium on User Interface Software and Technology, pp
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:41:53.103068Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 50bc6b1c-d234-463a-89f7-0ea1aeb79db7 · outbound
This paper cites Large Language Models Perform Diagnostic Reasoning.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Large Language Models Perform Diagnostic Reasoning
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T21:36:52.384146Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 3cb5697e-cea7-4fca-8936-27bc01d45e1a · outbound
This paper cites MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning
Reference 17
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T21:36:52.374799Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 3f102d19-6d21-413d-af7b-8eade6e78125 · outbound
This paper cites ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
Reference 18
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T21:36:52.369906Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 1a6a6f27-68d6-4b5a-8c6d-27446e64585a · outbound
This paper cites Advances in Neural Information Processing Systems 35, 24824–24837 (2022).
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Advances in Neural Information Processing Systems 35, 24824–24837 (2022)
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:41:53.106256Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ef35f386-b49d-4051-89c1-c0d2990413b2 · outbound
This paper cites Multi-step Jailbreaking Privacy Attacks on ChatGPT.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Multi-step Jailbreaking Privacy Attacks on ChatGPT
Reference 20
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T21:36:52.522996Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ba88cf10-a96b-4307-8f2c-e877ff3e2726 · outbound
This paper cites In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT
Reference 21
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T21:36:52.393660Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 4b7e8fc8-a251-4518-9670-6ab5593c6d32 · outbound
This paper cites AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
Reference 22
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T21:36:52.453943Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ef1d3bf9-f50f-4b5e-be1a-336db1a2e088 · outbound
This paper cites Automatically Auditing Large Language Models via Discrete Optimization.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Automatically Auditing Large Language Models via Discrete Optimization
Reference 23
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T21:36:52.469255Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation c058c589-b1a6-4851-92fd-d14f34da76e6 · outbound
This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 24
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T21:36:52.491112Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ebb79019-4428-4388-acd3-2fcb2098df84 · outbound
This paper cites AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models
Reference 25
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T21:36:52.459033Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a5be04eb-7089-4b62-a33c-3f3cd94f841e · outbound
This paper cites MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots
Reference 26
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T21:36:52.533755Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 921a1417-8384-499b-97e9-4bdae34b8f08 · outbound
This paper cites Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations
Reference 27
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T21:36:52.479691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation f92ea18d-b282-49f0-94a7-78cc624a958d · outbound
This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Jailbreaking Black Box Large Language Models in Twenty Queries
Reference 28
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T21:36:52.473897Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 51bae0dc-effd-4724-9804-6e3ad33b4bdb · outbound
This paper cites Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation
Reference 29
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T21:36:52.516771Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation de79b5a9-c7fc-4908-8bde-64d2917fcd92 · outbound
This paper cites Query-Based Adversarial Prompt Generation.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Query-Based Adversarial Prompt Generation
Reference 30
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T21:36:52.402868Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation cb1b8fd8-a396-4c50-8c2c-42e2b2672dbc · outbound
This paper cites CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
Reference 31
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T21:36:52.485500Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 5c51fca5-3ace-4ed8-aead-76b29948150c · outbound
This paper cites DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
Reference 32
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T21:36:52.445155Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 9f740cc8-976e-4e1b-bdac-fa4eb26f8472 · outbound
This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
Reference 33
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T21:36:52.497769Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 7c05e2e6-6f84-4eb6-bb9b-85156b3002b6 · outbound
This paper cites arXiv preprint arXiv:2402.10601 (2024).
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs arXiv preprint arXiv:2402.10601 (2024)
Reference 34
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T21:36:52.528600Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 44863539-cf70-48cd-8278-ea533d6fc824 · outbound
This paper cites Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
Reference 35
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T21:36:52.440502Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 373986f5-47b5-4ec7-93f6-d1525fb8a244 · outbound
This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Reference 36
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T21:36:52.464182Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8c116005-d260-42e6-8d32-f524cffab5ee · outbound
This paper cites In: Theory and Applications of Ontology: Computer Applications, pp.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs In: Theory and Applications of Ontology: Computer Applications, pp
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:41:53.109543Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 2ef11fd6-9aae-4990-9fe3-7a91b7b30593 · outbound
This paper cites In: 2014 47th Hawaii International Conference on System Sciences, pp.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs In: 2014 47th Hawaii International Conference on System Sciences, pp
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:41:53.112843Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8be137c6-aaf8-4f99-bbaf-974704d4df07 · outbound
This paper cites IEEE transactions on neural networks and learning systems 33(2), 494–514 (2021).
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs IEEE transactions on neural networks and learning systems 33(2), 494–514 (2021)
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.472555Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b7468a20-16ed-4857-afa4-b956386523d6 · outbound
This paper cites In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.480798Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a66af267-0a44-4fc0-aa9b-494d07cbae49 · outbound
This paper cites Advances in Neural Information Processing Systems 36 (2024).
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Advances in Neural Information Processing Systems 36 (2024)
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.498417Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation abe688da-d2bf-4bcd-98bb-5fbcb186008c · outbound
This paper cites https://lmsys.org/blog/2023-06-29-longchat.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs https://lmsys.org/blog/2023-06-29-longchat
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.476942Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 0c06697e-3193-432c-a10b-b2c16b5bac22 · outbound
This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Llama 2: Open Foundation and Fine-Tuned Chat Models
Reference 43
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T21:36:52.510207Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a0822686-31bd-454d-b969-6fbc4d60c89f · outbound
This paper cites an unresolved cited work.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Unresolved cited work
Reference 44
- Resolution
- unresolved
- raw_fallback, observed 2026-05-18T21:42:51.489696Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b0039adb-b194-496e-abf9-8576f5d0ec47 · outbound
This paper cites GPT-4 Technical Report.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs GPT-4 Technical Report
Reference 45
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T21:36:52.419620Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8fee8f1f-2c85-4974-8f40-39948f62a05c · outbound
This paper cites GPT-4o System Card.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs GPT-4o System Card
Reference 46
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T21:36:52.449485Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 163d61af-a4ed-4caa-b19a-cd8c1d5de4f5 · outbound
This paper cites Claude-3.5 Model Card (2024).
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Claude-3.5 Model Card (2024)
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:42:51.493727Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 4752f6a6-2bfc-40c6-98c3-dc21c202560e · outbound
This paper cites Language models are unsupervised multitask learners.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Language models are unsupervised multitask learners
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:41:53.130547Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b543987c-e8c9-430d-aa1e-8975058769ab · outbound
This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Reference 49
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T21:36:52.424978Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 7604c940-8b49-4e38-a32e-a5341efb20e0 · outbound
This paper cites MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
Reference 50
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T21:36:52.435410Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 334cbcc0-699e-4b65-9c26-658840696e42 · outbound
This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Reference 51
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T21:36:52.414153Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 0716171d-da89-43a0-b878-46b3aa7e47b1 · outbound
This paper cites an unresolved cited work.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Unresolved cited work
Reference 52
- Resolution
- unresolved
- raw_fallback, observed 2026-05-18T21:41:53.133327Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 2b7a8093-461b-4ecc-ba4e-569bd2e286d8 · outbound
This paper cites Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
Reference 53
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T21:36:52.409545Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation adda398d-c0ac-4c98-aa65-02f01bfa6911 · outbound
This paper cites Efficient Estimation of Word Representations in Vector Space.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Efficient Estimation of Word Representations in Vector Space
Reference 54
- Resolution
- malformed identifier
- local_arxiv, observed 2026-05-18T21:36:52.398224Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 6b0ef2a5-16a2-4f21-9b3f-45dcef4a85ac · outbound
This paper cites an unresolved cited work.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Unresolved cited work
Reference 55
- Resolution
- unresolved
- raw_fallback, observed 2026-05-18T21:42:51.465212Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 091d8c05-5855-4ce3-8e87-5d9326de851b · outbound
This paper cites an unresolved cited work.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Unresolved cited work
Reference 56
- Resolution
- unresolved
- raw_fallback, observed 2026-05-18T21:42:51.484712Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 65b22d6d-10c3-45fd-b5e9-47d298672b08 · outbound
This paper cites an unresolved cited work.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Unresolved cited work
Reference 57
- Resolution
- unresolved
- raw_fallback, observed 2026-05-18T21:41:53.122021Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a181bf21-cda8-432b-904f-0edbfca095ec · outbound
This paper cites <Example 3> Domains: Education, Consumer services Scenarios: AI systems may be difficult to interpret, leading to incorrect eval- uations or distrust among users.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs <Example 3> Domains: Education, Consumer services Scenarios: AI systems may be difficult to interpret, leading to incorrect eval- uations or distrust among users
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:41:53.124993Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 0fa1df22-167a-4d4f-8988-24f4c43ac3e8 · outbound
This paper cites an unresolved cited work.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Unresolved cited work
Reference 59
- Resolution
- unresolved
- raw_fallback, observed 2026-05-18T21:41:53.127482Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a29274c5-f99d-46df-8c77-0dc20a427d0a · outbound
This paper cites an unresolved cited work.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Unresolved cited work
Reference 60
- Resolution
- unresolved
- raw_fallback, observed 2026-05-18T21:41:53.115821Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e7ccb396-daa3-4203-8ba9-2295ed8999fd · outbound
This paper cites Stay in Character!.
GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs Stay in Character!
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-18T21:41:53.119075Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Pith citing papers
Observation cc542535-d662-4c85-8865-a815766dbdf2 · inbound
Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models cites this paper.
Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs
Reference 28
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T03:42:01.658650Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.