Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-10T22:53:20.963955Z
Paper Citation Record · LEDGER
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense
As of 12 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2501.00517.
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
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
26 of 26 outbound references displayed
- verified exact0
- verified fuzzy3
- unresolved23
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 31561fc9-05c1-44cb-bacf-fbb7550e4640 · outbound
This paper cites Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.344092Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 087a0014-2e97-4466-9c8b-600f6881ab33 · outbound
This paper cites Can LLM-Generated Misinformation Be Detected?.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Can LLM-Generated Misinformation Be Detected?
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.372871Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9c9485fd-3d9b-48a2-a535-f7d52dd85d64 · outbound
This paper cites Foundational Challenges in Assuring Alignment and Safety of Large Language Models.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Foundational Challenges in Assuring Alignment and Safety of Large Language Models
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.428520Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bdc615e5-ee8f-44f9-88ff-58dd2205d023 · outbound
This paper cites Scaling Instruction-Finetuned Language Models.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Scaling Instruction-Finetuned Language Models
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.480547Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2d85b8b3-0060-4a14-8675-58054c37313f · outbound
This paper cites Training language models to follow instructions with human feedback.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Training language models to follow instructions with human feedback
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.557650Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fe6fb275-3db4-472c-97dd-84e84362f4b5 · outbound
This paper cites Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.585262Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 375f6167-abdc-4ad2-a10b-031127dcf45c · outbound
This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.610290Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 77e9c73c-6acf-4760-b655-cab31d36e36a · outbound
This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense KTO: Model Alignment as Prospect Theoretic Optimization
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.621497Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fb1d6030-b4c2-4c56-9435-800cc824a30b · outbound
This paper cites Beavertails: Towards improved safety alignment of llm via a human - preference dataset.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Beavertails: Towards improved safety alignment of llm via a human - preference dataset
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T22:53:21.679484Z
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 aa68c2c4-eda7-44fe-a71c-452ae2bd883d · outbound
This paper cites Safe RLHF: Safe Reinforcement Learning from Human Feedback.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Safe RLHF: Safe Reinforcement Learning from Human Feedback
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.636788Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f0db6692-c76b-48b3-b8b8-14609638632d · outbound
This paper cites SecAlign: Defending Against Prompt Injection with Preference Optimization.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense SecAlign: Defending Against Prompt Injection with Preference Optimization
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.639962Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c5d680cc-0042-4fe3-b989-cce3c0ef94c0 · outbound
This paper cites DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.644003Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d671b371-d266-4ce3-87f8-5be94a9224b0 · outbound
This paper cites Superficial Safety Alignment Hypothesis.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Superficial Safety Alignment Hypothesis
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.650695Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c3bbda7f-1a48-422f-97ce-e35bce0d84c7 · outbound
This paper cites Safety Layers in Aligned Large Language Models: The Key to LLM Security.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Safety Layers in Aligned Large Language Models: The Key to LLM Security
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T22:53:21.668623Z
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 e796599c-3564-4d6a-96ca-4edc5fbbd1cd · outbound
This paper cites Multilingual Jailbreak Challenges in Large Language Models.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Multilingual Jailbreak Challenges in Large Language Models
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.662431Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a82aabb7-4b40-4daa-a556-e8e0d0903a6b · outbound
This paper cites SafetyBench: Evaluating the Safety of Large Language Models.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense SafetyBench: Evaluating the Safety of Large Language Models
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.710337Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 502968ec-c692-4812-b17d-d6c4964ee2d8 · outbound
This paper cites CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.778379Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3c2d03b5-39a7-4daf-9977-694f7bab023b · outbound
This paper cites S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.842188Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4e73d1ec-f0c0-4127-af19-9d94cf0b1394 · outbound
This paper cites A Post-Training Enhanced Optimization Approach for Small Language Models.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense A Post-Training Enhanced Optimization Approach for Small Language Models
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T22:53:21.614718Z
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 4a17f408-296d-49d9-a27a-5a28bccd50cc · outbound
This paper cites Safety Assessment of Chinese Large Language Models.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Safety Assessment of Chinese Large Language Models
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T22:53:20.901818Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b273681b-e41e-46a8-9ac5-55a50aa3bb35 · outbound
This paper cites an unresolved cited work.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Unresolved cited work
Reference 21
- Resolution
- unresolved
- raw_fallback, observed 2026-08-10T22:53:21.546684Z
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 3e6070bb-a32a-4651-8914-a3630ceefd27 · outbound
This paper cites an unresolved cited work.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Unresolved cited work
Reference 22
- Resolution
- unresolved
- raw_fallback, observed 2026-08-10T22:53:21.344711Z
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 d97dc54b-3a49-48ad-9948-f7eb9dc9cae8 · outbound
This paper cites an unresolved cited work.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Unresolved cited work
Reference 23
- Resolution
- unresolved
- raw_fallback, observed 2026-08-10T22:53:21.267410Z
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 e3800634-b248-4896-93cb-531948b027f4 · outbound
This paper cites an unresolved cited work.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Unresolved cited work
Reference 24
- Resolution
- unresolved
- raw_fallback, observed 2026-08-10T22:53:21.256475Z
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 c0877385-0913-4394-9198-bce4417cd12c · outbound
This paper cites an unresolved cited work.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Unresolved cited work
Reference 25
- Resolution
- unresolved
- raw_fallback, observed 2026-08-10T22:53:21.246408Z
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 29c8aaf3-22fd-4f92-ac75-196ad80bdcca · outbound
This paper cites an unresolved cited work.
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense Unresolved cited work
Reference 26
- Resolution
- unresolved
- raw_fallback, observed 2026-08-10T22:53:21.236077Z
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
No inbound Pith citation observations are available.