Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions | Paper Citation Record

Observation 4b04799a-7e9e-4ea8-893f-cfc2a76a5cbb · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-30T20:10:58.635743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95eb2da0-9811-46e9-87b0-374b35a06797 · outbound

This paper cites J.; and Wong, E.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions J.; and Wong, E

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-30T20:10:58.693255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation beefb022-6855-4651-9d9f-dd3cf6116c65 · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-30T20:10:58.749563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d87a9bf6-8131-4830-a09a-34654ee838f4 · outbound

This paper cites N.; Padmakumar, A.; Rebedea, T.; Varghese, J.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions N.; Padmakumar, A.; Rebedea, T.; Varghese, J

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-30T20:10:58.806235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d630a9e-32d8-461b-8e1a-2c5e4731c2c2 · outbound

This paper cites Y.; Lambert, N.; Choi, Y.; and Dziri, N.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Y.; Lambert, N.; Choi, Y.; and Dziri, N

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-30T20:10:59.061991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 203007c2-5447-485e-bf87-8a61713f8ae7 · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-30T20:10:59.204766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b4f2678-2f52-4673-9551-11e5e072cd88 · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-30T20:10:59.375323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 332e71d9-acea-4cfe-9ce7-3d338096f234 · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-30T20:10:59.590214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f35373a8-ce36-41bb-948e-058f747cdad3 · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-30T20:10:59.710487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ca73399-20c4-449b-aa2d-74bf9b4b1be5 · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-30T20:10:59.964686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53eea988-3a68-423c-9892-bb2f7a761413 · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.078531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80642b6c-5ecd-4e1c-9383-f4e3842c023b · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.228624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12f1c9f5-62cc-4597-9587-4c7975f2bbcf · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.377746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fbd5d3f-2e29-49cc-922f-f68346acd876 · outbound

This paper cites R.; Palangi, H.; Chang, K.-W.; Choi, Y.; and Gabriel, S.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions R.; Palangi, H.; Chang, K.-W.; Choi, Y.; and Gabriel, S

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.494319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe8f6620-6d8a-4cf7-be45-ddb55e9a98bb · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.550082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d41aa80f-521f-4c0e-86a4-8b746013c219 · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.668693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90926020-1ae0-4115-9593-b0c21e493868 · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.707303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4419244d-b7c0-4c12-9b51-37459f1e67db · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.710607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7633a12f-e4fc-43fa-b15a-d28a37444349 · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.717117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0306bb7-5108-4f32-bb88-2737b13d4881 · outbound

This paper cites V.; Zhou, D.; et al.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions V.; Zhou, D.; et al

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.719851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce33fec6-2db2-460c-9ca2-e19aaf14908c · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.722592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d5b0c7c-4002-48db-beb7-f126da137905 · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.725597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f756d820-ebbf-47bd-9c2f-6114608ced2f · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.728637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30bb70da-4547-4bc8-883f-e64659573590 · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.738383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aac9803e-c520-4528-b253-86e695115fbb · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.741392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 513919bd-00fd-47bc-bdec-7f15550b3655 · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.747130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b25389d1-b124-4a0d-ba5e-2d5431f5cb44 · outbound

This paper cites B.; and Gan, C.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions B.; and Gan, C

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.750199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62af4e16-8249-441a-b8cb-06078e9468db · outbound

This paper cites an unresolved cited work.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.753104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a43f385e-5450-4710-9dee-f047eaca764d · outbound

This paper cites https://www.anthropic.com/news/introducing-claude , year=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions https://www.anthropic.com/news/introducing-claude , year=

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.768236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa3a0831-b16a-4825-83b9-e7d82183d983 · outbound

This paper cites Qwen3 Technical Report.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Qwen3 Technical Report

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.770982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ac580b4-e13f-4f0e-b00a-b720d0cac06b · outbound

This paper cites DeepSeek-V3 Technical Report.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions DeepSeek-V3 Technical Report

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.774016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12f56da9-e660-4447-bbc9-fe1729953b16 · outbound

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

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.777417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 935d5775-c0f1-43a7-94dc-6a862edaf1a4 · outbound

This paper cites ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.780508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0582f64-2058-4f80-a9a8-0d8532b09889 · outbound

This paper cites Proceedings of the 2023 conference on empirical methods in natural language processing , pages=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Proceedings of the 2023 conference on empirical methods in natural language processing , pages=

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.783605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30b5b061-3b76-4a61-a932-33f0bc455a4d · outbound

This paper cites Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.786338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a520c33b-0f4a-4d1c-9888-2ec1a004ccb0 · outbound

This paper cites The Eleventh International Conference on Learning Representations , year=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions The Eleventh International Conference on Learning Representations , year=

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.789997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d649c760-25b7-4320-a791-7c210f302de8 · outbound

This paper cites Findings of the Association for Computational Linguistics: EMNLP 2023 , pages=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Findings of the Association for Computational Linguistics: EMNLP 2023 , pages=

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.792988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f15509d0-d7ea-438d-b09b-9aa2e246a702 · outbound

This paper cites Advances in neural information processing systems , volume=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Advances in neural information processing systems , volume=

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.795950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b0c5ac8-08df-44e2-a26d-d3df18ea74b1 · outbound

This paper cites Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages=

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.799112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38b291c1-42cb-430d-8c5c-1e37555129ea · outbound

This paper cites Neurips Safe Generative AI Workshop 2024 , year=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Neurips Safe Generative AI Workshop 2024 , year=

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.802053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcff6aa1-7845-4ff5-a544-76e57401ae84 · outbound

This paper cites arXiv preprint arXiv:2506.19676 , year=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions arXiv preprint arXiv:2506.19676 , year=

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.804864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 781c9b36-9474-4298-80a9-a5729eacc2cd · outbound

This paper cites GPT-4 Technical Report.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions GPT-4 Technical Report

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.807643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26d10d7b-245f-4d3e-ba49-196feb191fce · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.810168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa5e468f-e854-4bdc-96f0-3cc8ca3e3c16 · outbound

This paper cites The Llama 3 Herd of Models.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions The Llama 3 Herd of Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.814297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90cd18b6-7d05-4ac7-bab3-9f916bb123b9 · outbound

This paper cites Advances in neural information processing systems , volume=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Advances in neural information processing systems , volume=

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.817416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b4bb89b-cb2d-4865-b68b-74e0ba5627b8 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Constitutional AI: Harmlessness from AI Feedback

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.820174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dda64bf7-ba1c-4f5e-87e6-6f5b8b6c4f10 · outbound

This paper cites Advances in neural information processing systems , volume=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Advances in neural information processing systems , volume=

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.823275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5741105d-70c7-456d-8104-798747687844 · outbound

This paper cites 11th International Conference on Learning Representations, ICLR 2023 , year=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions 11th International Conference on Learning Representations, ICLR 2023 , year=

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.826054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb93efb9-a43d-4713-a883-e8687d47aca0 · outbound

This paper cites Advances in neural information processing systems , volume=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Advances in neural information processing systems , volume=

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.829084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03a360ea-7e0d-4b07-97ef-3758f8313e82 · outbound

This paper cites ICLR 2024 Workshop on Large Language Model (LLM) Agents , year=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions ICLR 2024 Workshop on Large Language Model (LLM) Agents , year=

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.832172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68eb0662-519c-487d-a6b5-50dcfdf73d2f · outbound

This paper cites International Conference on Learning Representations , volume=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions International Conference on Learning Representations , volume=

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.835432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9482df31-27d0-4206-a1f2-f1a590ad2f73 · outbound

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

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.838280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d42f255-50f0-4122-af6a-9515a66fec9f · outbound

This paper cites Advances in neural information processing systems , volume=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Advances in neural information processing systems , volume=

Reference 71

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.840993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b87a18f-da10-46bc-9c18-bfe1fcff9959 · outbound

This paper cites 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) , pages=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) , pages=

Reference 72

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.843859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f707a609-2bdb-4be6-9558-68465fffefa5 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Advances in Neural Information Processing Systems , volume=

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.846981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d99b3b0e-af2a-4721-9707-823f31016ba3 · outbound

This paper cites International Conference on Learning Representations , volume=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions International Conference on Learning Representations , volume=

Reference 74

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.849735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 260d5672-0e39-46d5-a9cd-1e57f9513e2e · outbound

This paper cites 33rd USENIX Security Symposium (USENIX Security 24) , year =.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions 33rd USENIX Security Symposium (USENIX Security 24) , year =

Reference 75

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.852576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba4ba950-383e-45af-b2ca-ed80ef13e0aa · outbound

This paper cites 34th USENIX Security Symposium (USENIX Security 25) , pages=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions 34th USENIX Security Symposium (USENIX Security 25) , pages=

Reference 76

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.855343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc1cc635-b8c1-421b-90e9-9363af1ad12d · outbound

This paper cites Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM

Reference 77

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.858023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dda0d18-01d8-4863-b6f8-a5e5639c331d · outbound

This paper cites Red Teaming GenAI: What Can We Learn from Adversaries? , year=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Red Teaming GenAI: What Can We Learn from Adversaries? , year=

Reference 78

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.860629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e81f7334-9d2e-41f3-bb17-f9a0c649a8ad · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2025 , pages=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Findings of the Association for Computational Linguistics: ACL 2025 , pages=

Reference 79

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.863400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3e3c374-3480-4379-9822-543521e36928 · outbound

This paper cites Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 80

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.866236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86487206-81ba-4049-9915-85cf968b6c41 · outbound

This paper cites Second Conference on Language Modeling , year=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Second Conference on Language Modeling , year=

Reference 81

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.869658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d745e40b-7c4b-4bc9-927c-b87461448464 · outbound

This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 82

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.872400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 674969db-c7f5-4be9-a03b-a365a16197d4 · outbound

This paper cites arXiv preprint arXiv:2601.20903 , year=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions arXiv preprint arXiv:2601.20903 , year=

Reference 83

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.875355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0baaf9e3-a3da-45fd-9117-c5c074ef5db7 · outbound

This paper cites Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search

Reference 84

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.877932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 827e16a9-8ddc-4718-9556-0f5e74388612 · outbound

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

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 85

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.880602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a306d267-eafa-4c93-9d8e-1846f83c4c53 · outbound

This paper cites Advances in neural information processing systems , volume=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Advances in neural information processing systems , volume=

Reference 86

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.883238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0fa777e-01e2-4390-a66c-077a15c30b3b · outbound

This paper cites ShieldGemma: Generative AI Content Moderation Based on Gemma.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions ShieldGemma: Generative AI Content Moderation Based on Gemma

Reference 87

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.885849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed0c3849-3f89-460d-9de2-e723ffc92b01 · outbound

This paper cites Qwen3Guard Technical Report.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Qwen3Guard Technical Report

Reference 88

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.888291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 179e612a-7c79-4714-acc0-b4ed86173224 · outbound

This paper cites Neurips Safe Generative AI Workshop 2024 , year=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Neurips Safe Generative AI Workshop 2024 , year=

Reference 89

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.891218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60b961d5-0b2a-4270-b6d6-8ddc72b160b5 · outbound

This paper cites Proceedings of the 31st International Conference on Computational Linguistics , pages=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Proceedings of the 31st International Conference on Computational Linguistics , pages=

Reference 90

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.893973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0dc5397-0492-4fec-a2ac-d5f2e3431b10 · outbound

This paper cites arXiv preprint arXiv:2509.26345 , year=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions arXiv preprint arXiv:2509.26345 , year=

Reference 91

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.896950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67a46615-752b-437d-a974-d2ea99e7ec37 · outbound

This paper cites Second Workshop on Agents in the Wild: Safety, Security, and Beyond , year=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Second Workshop on Agents in the Wild: Safety, Security, and Beyond , year=

Reference 92

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.899832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82767835-094e-46f9-aa06-f2f568482527 · outbound

This paper cites THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models

Reference 93

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.902525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c495ee18-a10f-44ed-8641-5329942d9ac6 · outbound

This paper cites 0: A diverse ai safety dataset and risks taxonomy for alignment of llm guardrails , author=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions 0: A diverse ai safety dataset and risks taxonomy for alignment of llm guardrails , author=

Reference 94

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.905231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 986e7d97-588e-47c2-8889-3b4b14ea3acd · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 95

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.908002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7053110e-fbad-4572-acfb-bcda29feb0bc · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Advances in Neural Information Processing Systems , volume=

Reference 96

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.911046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdfdea83-5be2-4649-a919-2f44721edf1e · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Advances in Neural Information Processing Systems , volume=

Reference 97

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.913908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 754fa630-378c-49ed-9692-9ed5b6c1dec2 · outbound

This paper cites International Conference on Learning Representations , volume=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions International Conference on Learning Representations , volume=

Reference 98

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.916633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebea8a40-8b99-4396-8cd8-b56c0929cae9 · outbound

This paper cites Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

Reference 99

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.919374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38cdd77d-fbb6-4eb6-923d-64af12f45788 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Advances in Neural Information Processing Systems , volume=

Reference 100

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.922163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f8c4f48-0118-4aa6-b2b1-ddb2dd676df9 · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2024 , pages=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Findings of the Association for Computational Linguistics: ACL 2024 , pages=

Reference 101

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.925005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd49ad74-eb83-48dc-8999-60f30759da95 · outbound

This paper cites Proceedings of the 47th international ACM SIGIR conference on research and development in information retrieval , pages=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Proceedings of the 47th international ACM SIGIR conference on research and development in information retrieval , pages=

Reference 102

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.928017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a757a35e-e8b1-48e1-95a3-284d8d8e11e4 · outbound

This paper cites Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , pages=.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 103

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.931174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c6a2151-4ae2-41bf-b554-84ba6e4f3f47 · outbound

This paper cites LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models

Reference 104

Resolution: unresolved; no resolver link, observed 2026-07-30T20:11:00.934085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers