MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security | Paper Citation Record

Observation 9dc5398e-f585-4da2-9d83-c20d7a04e93f · outbound

This paper cites Mogu: A framework for enhancing safety of llms while preserving their usability,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Mogu: A framework for enhancing safety of llms while preserving their usability,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:09:42.077038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4bb66a28-3120-4825-b8da-f5254d3cd532 · outbound

This paper cites Gpt-4 technical report,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Gpt-4 technical report,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.418878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1558a58-a354-443b-b40a-f503ba477256 · outbound

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

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.421041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edc29ab5-a9a5-4367-a3c0-04ee523c00e2 · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.423390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c0d83d0-d2b6-471f-a4a5-fae1eb0f28cd · outbound

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

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.426641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc764439-8a44-4e88-95b7-ec1d378ff20f · outbound

This paper cites FLIRT: Feedback Loop In-context Red Teaming.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security FLIRT: Feedback Loop In-context Red Teaming

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.429359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 403519d2-2a8b-4bc2-8ae3-e9693caa9657 · outbound

This paper cites Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.432374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ead34801-dcd9-434d-b7cf-10580f06e3e0 · outbound

This paper cites A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.435223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12cedbfb-1706-4921-8499-8150a0757aaa · outbound

This paper cites Lima: Less is more for alignment,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Lima: Less is more for alignment,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:09:42.063715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 02db291a-5a5d-4e42-af66-a501dd18c588 · outbound

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

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Training language models to follow instructions with human feedback,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.440287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb86b84a-ac4c-4939-9349-a3745d597338 · outbound

This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.442984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 262bc832-9a17-474f-8b41-3324f2f1f943 · outbound

This paper cites A comprehensive study of jailbreak attack versus defense for large language models,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security A comprehensive study of jailbreak attack versus defense for large language models,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:09:42.050203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8f4adb80-c946-4fdf-a9cc-2de908f44f53 · outbound

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

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.448210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce4ffc35-5ad8-47fc-81f3-d207b73311b6 · outbound

This paper cites LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.450991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c917c07-f06e-4e09-9d7a-21b822e1d425 · outbound

This paper cites Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.453737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af156b49-2e8e-48a1-b665-2b82b8b86dd3 · outbound

This paper cites Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.456061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d039875-38b8-4456-ac5f-702912bac0dd · outbound

This paper cites Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-04T23:09:41.896274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 12afa9f2-8495-4ea5-a717-ffd7c39d6a48 · outbound

This paper cites Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.460875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a575274-5666-4764-9913-0df741e67ef7 · outbound

This paper cites Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.463474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98df20ed-9ab8-4277-9bf6-30125ef8485f · outbound

This paper cites The Llama 3 Herd of Models.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security The Llama 3 Herd of Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.465759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f161f21a-9365-4361-ab7b-725b7b14fb53 · outbound

This paper cites A holistic approach to undesired content detection in the real world,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security A holistic approach to undesired content detection in the real world,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:09:42.040961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 881ed3e0-8875-48cf-a485-a295d796bf27 · outbound

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

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.470662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1eebe795-ea34-4255-a580-d7a0b4b0d66b · outbound

This paper cites Certifying LLM Safety against Adversarial Prompting.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Certifying LLM Safety against Adversarial Prompting

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.473339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b5417fd-5bef-4bc5-8652-0547f8590e12 · outbound

This paper cites Lightweight safety guardrails using fine-tuned bert embeddings,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Lightweight safety guardrails using fine-tuned bert embeddings,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.475614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0986a88f-38f8-4ea1-9def-a33b45ba276e · outbound

This paper cites SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.478401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3c0882b-84ae-4945-a51d-c351a28d9757 · outbound

This paper cites Navigating the OverKill in Large Language Models.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Navigating the OverKill in Large Language Models

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-04T23:09:41.840571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 10a3c887-315a-40de-a43f-b04723e1dbe2 · outbound

This paper cites Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.483523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cfb6400-5c9e-4148-bcae-beb5aafdf18e · outbound

This paper cites Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.485922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b83ca1f-1e85-426b-b604-e817fe22386e · outbound

This paper cites Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.488370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef3557ae-8039-45ce-8b44-83a2979f2965 · outbound

This paper cites Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.491116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0abc586-af39-432a-8053-36a2ccc3571d · outbound

This paper cites A Survey on Mixture of Experts in Large Language Models.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security A Survey on Mixture of Experts in Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.493535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4632282d-a94f-4fc2-b241-76f34871da81 · outbound

This paper cites Uni-moe: Scaling unified multimodal llms with mixture of experts,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Uni-moe: Scaling unified multimodal llms with mixture of experts,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.495912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8371582d-84ec-4ec6-b30c-437d0b14014e · outbound

This paper cites OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.498475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6e098f9-c354-479b-b8f2-9964ef0d3085 · outbound

This paper cites How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.500858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9becc34-a79c-413b-b080-229bd19f3777 · outbound

This paper cites Red Teaming Language Models with Language Models.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Red Teaming Language Models with Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.503307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 426a32ea-c602-491d-9fc6-da5b8952a489 · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.505782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f56caf1-de30-425d-a0ec-e7d7fabde360 · outbound

This paper cites Explore, Establish, Exploit: Red Teaming Language Models from Scratch.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Explore, Establish, Exploit: Red Teaming Language Models from Scratch

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.508015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fe51abf-e933-4e20-802a-28412b67252e · outbound

This paper cites Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.510729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64bd5f15-fa7e-4f0d-b2ed-e26b626adbd3 · outbound

This paper cites Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.513177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6ba4a17-9d7e-4a19-8b37-598ca4bf46c7 · outbound

This paper cites COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.515431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fef8e249-e825-45c4-9063-a5adb4df700e · outbound

This paper cites Jailbroken: How does llm safety training fail?.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Jailbroken: How does llm safety training fail?

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.517713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe644a2a-601f-4f18-b136-82dca3400e09 · outbound

This paper cites Automatically auditing large language models via discrete optimization,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Automatically auditing large language models via discrete optimization,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:09:42.023516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a6efadde-989c-4147-8d82-5b3e79debe8b · outbound

This paper cites Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.522170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efbff674-42ba-4754-b406-ece032bb95c6 · outbound

This paper cites Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.524212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8277e1ce-0848-4875-b947-5de95d990291 · outbound

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

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.526476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fed6c88-2376-428a-bba4-3f70b0047335 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.528615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60840032-8432-4455-8d31-8136cb96982e · outbound

This paper cites Removing RLHF Protections in GPT-4 via Fine-Tuning.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Removing RLHF Protections in GPT-4 via Fine-Tuning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.530996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0746e8d6-ca2d-490b-bf08-d3c599108cad · outbound

This paper cites A survey on large language model (llm) security and privacy: The good, the bad, and the ugly,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security A survey on large language model (llm) security and privacy: The good, the bad, and the ugly,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.533142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a343dbb-5ea4-4ee0-8f64-0f9446a2b4ad · outbound

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

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Defending chatgpt against jailbreak attack via self-reminder,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.535213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b551ba0-8dcc-4009-9481-9a872dae0065 · outbound

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

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.537604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41b7dcb4-1a29-42f4-825f-7e6bcf4fb978 · outbound

This paper cites LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.540879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27d14d86-01b1-421c-a413-6a07a1aa0db2 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security LoRA: Low-Rank Adaptation of Large Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.543359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16c5c855-997c-46f1-a7ea-85d38f328d70 · outbound

This paper cites Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.545861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10d452d0-ad48-457a-9e2f-2a8516dd405b · outbound

This paper cites A Closer Look into Mixture-of-Experts in Large Language Models.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security A Closer Look into Mixture-of-Experts in Large Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.548125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5381ff8e-c8a9-4738-95c8-afc06896dcd8 · outbound

This paper cites Adaptive Attention Span in Transformers.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Adaptive Attention Span in Transformers

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.550995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e54ab47-115d-4f55-8f27-43baeb65ec61 · outbound

This paper cites Is On-Device AI Broken and Exploitable? Assessing the Trust and Ethics in Small Language Models.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Is On-Device AI Broken and Exploitable? Assessing the Trust and Ethics in Small Language Models

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-08-04T23:09:41.679537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 236bfd5a-4043-4a69-9b94-c05979f94c3b · outbound

This paper cites The hidden risks of large reasoning models: A safety assessment of r1,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security The hidden risks of large reasoning models: A safety assessment of r1,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.556460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3817d6ae-1a90-4122-ad7d-1712b98f17b0 · outbound

This paper cites Falcon-40B: an open large language model with state-of-the-art performance,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Falcon-40B: an open large language model with state-of-the-art performance,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:09:42.004374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1e150241-98f4-4055-aadf-150db08c3e80 · outbound

This paper cites Qwen2 technical report,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Qwen2 technical report,

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:09:41.995121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 72b6ea39-32e3-4be0-9da5-bd150d90686a · outbound

This paper cites Qwen2.5: A party of foundation models,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Qwen2.5: A party of foundation models,

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.563287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f203041f-f3e2-43da-91ea-3b60b6da5816 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.565548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccb3ab6d-60ab-4875-8b4e-ea684f463a66 · outbound

This paper cites DeepSeek-V3 Technical Report.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security DeepSeek-V3 Technical Report

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.568088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f663f21d-6fa0-4780-abeb-cc0ad5f7768c · outbound

This paper cites The unlocking spell on base llms: Rethinking alignment via in-context learning,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security The unlocking spell on base llms: Rethinking alignment via in-context learning,

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-04T23:09:41.982843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f4736afa-cf44-4f03-8fef-46af2cc792f0 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Training Verifiers to Solve Math Word Problems

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.573265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89dce95f-0d2c-4792-9e61-17f46f8792bb · outbound

This paper cites SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.575944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66f4bc15-23dc-4d73-aba2-5d4f2540df54 · outbound

This paper cites Advancing LLM Reasoning Generalists with Preference Trees.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Advancing LLM Reasoning Generalists with Preference Trees

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.578345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4af7982f-a890-4203-9d1f-94fefb2fb084 · outbound

This paper cites Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.580806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc050fd4-0ae3-4005-a987-602c34e7b2ed · outbound

This paper cites Language models are super mario: Absorbing abilities from homologous models as a free lunch,.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security Language models are super mario: Absorbing abilities from homologous models as a free lunch,

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.583242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9694cb0d-1a26-4cb1-8a28-613fb8689937 · outbound

This paper cites The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-04T23:09:41.585521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b591270b-0b7d-4011-845c-880f0d93f679 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 70

Resolution: malformed identifier; no resolver link, observed 2026-08-04T23:09:41.587858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers