Paper Citation Record · LEDGER

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting

As of 12 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 10 inbound Pith citation observations for arXiv:2412.18826.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2412.18826 v1

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T04:29:04.378439Z

measured 59 of 59 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T05:56:46.433674Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-03T06:17:42.479409Z

Reference resolution

49 of 49 outbound references displayed

verified exact1
verified fuzzy6
unresolved42
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6baa617a-a4f4-4b89-92a2-be32a96b2837 · outbound

This paper cites GPT-4 Technical Report.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.173760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67733d41-6039-4a1c-98b0-ba43ace8a2d0 · outbound

This paper cites Flamingo: a Visual Language Model for Few-Shot Learning.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Flamingo: a Visual Language Model for Few-Shot Learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.180247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c27dd2a-74f2-4eee-bc20-5ba25ffa7ac4 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.188960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 907262f6-42d9-4032-a64d-4d7bdc1114c5 · outbound

This paper cites MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.192904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 888ca24e-d616-467c-bd5c-f3d9c84d0b96 · outbound

This paper cites Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.197170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bed33425-bb6a-4f3e-9b5a-95f0055d735e · outbound

This paper cites ShareGPT4V: Improving Large Multi-Modal Models with Better Captions.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.201656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7327c43e-ed4d-447f-a876-a31f0da02b23 · outbound

This paper cites DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.206077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8166c094-5a17-4d49-8779-8a293e676f6b · outbound

This paper cites Ml-lmcl: Mutual learning and large-margin contrastive learning for improving asr robust- ness in spoken language understanding.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Ml-lmcl: Mutual learning and large-margin contrastive learning for improving asr robust- ness in spoken language understanding

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:04.911431Z

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 392f7009-6275-44f6-bd3b-83e4e1cb95b7 · outbound

This paper cites Mrrl: Modifying the reference via reinforce- ment learning for non-autoregressive joint multiple intent de- tection and slot filling.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Mrrl: Modifying the reference via reinforce- ment learning for non-autoregressive joint multiple intent de- tection and slot filling

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:04.899788Z

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 cd6e04d5-3c0f-4094-8549-023b2f936181 · outbound

This paper cites InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.218991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c411e0a3-44bd-497c-b619-09706c66038d · outbound

This paper cites How Robust is Google's Bard to Adversarial Image Attacks?.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting How Robust is Google's Bard to Adversarial Image Attacks?

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.223101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba94d2ad-87e3-4ce3-81cb-a35a26d2d599 · outbound

This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.227612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a134b349-2279-4f04-b1dd-cc3d1a1ed253 · outbound

This paper cites A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.231658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86c6a18c-c7e6-4fe6-9688-fc3c4da0504d · outbound

This paper cites FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.239283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65c7b500-642c-474e-8abd-1da7b996eaee · outbound

This paper cites Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.242534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63354dae-02d6-4a71-afe0-f6fff5f03f1b · outbound

This paper cites Kwok, and Yu Zhang.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Kwok, and Yu Zhang

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:04.888015Z

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 dff344c9-5cd8-4ddb-84cb-7de1e8006646 · outbound

This paper cites Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.250720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 469a5641-c715-42c6-ac2f-8753d4cee5ea · outbound

This paper cites Mixtral of Experts.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Mixtral of Experts

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.254165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c715a99-f201-483a-b03c-42238a0c0150 · outbound

This paper cites BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.257920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b10f574c-ad5d-4809-a3fb-91e3a051cebb · outbound

This paper cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.262025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 090dcb47-7632-4966-8cf4-2a21c583fcec · outbound

This paper cites Improved Baselines with Visual Instruction Tuning.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Improved Baselines with Visual Instruction Tuning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.265743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 386541b2-9bd7-432d-aa37-93a0ce6742ed · outbound

This paper cites Visual Instruction Tuning.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Visual Instruction Tuning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:04.869696Z

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 58de8c53-5f0d-41a4-8fe0-f01c3065712c · outbound

This paper cites Chain of Hindsight Aligns Language Models with Feedback.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Chain of Hindsight Aligns Language Models with Feedback

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.272864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f762673-6a97-436e-a8ef-bf1376d411ed · outbound

This paper cites Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.276783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c63dedc9-657f-4ed6-9d02-882fb4667147 · outbound

This paper cites MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.280734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 001a728f-c1d1-479f-9d59-743bc432ad1a · outbound

This paper cites Safety of Multimodal Large Language Models on Images and Texts.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Safety of Multimodal Large Language Models on Images and Texts

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.285198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b7ea32b-b90d-49db-93ce-e1c47efb35a2 · outbound

This paper cites Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.288994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd60bbe5-a0e6-40ec-b189-29c4e755c7d0 · outbound

This paper cites GPT-4V(ision) as A Social Media Analysis Engine.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting GPT-4V(ision) as A Social Media Analysis Engine

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-08-11T04:29:04.593917Z

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 8c02c74b-b86a-430d-ab9b-41d3bc81fcf8 · outbound

This paper cites MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.300257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eea47d5f-710e-472f-8de9-98f708f27559 · outbound

This paper cites Visual Adversarial Examples Jailbreak Aligned Large Language Models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Visual Adversarial Examples Jailbreak Aligned Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.303378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1692b92b-1f0a-440f-9b26-c129a7460404 · outbound

This paper cites High-resolution image syn- thesis with latent diffusion models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting High-resolution image syn- thesis with latent diffusion models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.307550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ec45835-7eb5-4855-ac8c-6fe74e1c9ece · outbound

This paper cites On the adversar- ial robustness of multi-modal foundation models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting On the adversar- ial robustness of multi-modal foundation models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.311060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06f409dd-a52d-4d79-8f33-67a0fd0757e5 · outbound

This paper cites Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.314196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 152c8be4-b667-44a4-a94b-95663b27cc72 · outbound

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

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.317455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d729971c-cdc0-460d-9740-7b78eb486423 · outbound

This paper cites Safety Assessment of Chinese Large Language Models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Safety Assessment of Chinese Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.320763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dad78fb-1b18-4f9b-9192-0ec5d5424600 · outbound

This paper cites Hashimoto.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Hashimoto

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:04.845390Z

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 11a45985-491a-4ec9-a59f-ce1ddd405094 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting LLaMA: Open and Efficient Foundation Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.327171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36c3196c-d36c-4d9c-9ba2-9839c7216a56 · outbound

This paper cites CogVLM: Visual Expert for Pretrained Language Models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting CogVLM: Visual Expert for Pretrained Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.330178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24539c06-227e-423c-ba79-bcff85c264fa · outbound

This paper cites Aligning Large Language Models with Human: A Survey.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Aligning Large Language Models with Human: A Survey

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.334021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f070840-e5cc-4275-8512-fe00867ff612 · outbound

This paper cites Adashield: Safeguarding multimodal large lan- guage models from structure-based attack via adaptive shield prompting, 2024.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Adashield: Safeguarding multimodal large lan- guage models from structure-based attack via adaptive shield prompting, 2024

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:29:04.834792Z

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 ce98d3d6-cad0-478e-8b13-39397df9cdd7 · outbound

This paper cites Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.341285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cbbede5-4d35-4813-9b52-99abdb27a07a · outbound

This paper cites mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.345223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e6f838d-02ab-4977-9805-b95c311cc1d9 · outbound

This paper cites A Survey on Multimodal Large Language Models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting A Survey on Multimodal Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.349211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9888d776-7248-4ccd-86c2-5078ecf9f421 · outbound

This paper cites Woodpecker: Hallucination Correction for Multimodal Large Language Models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Woodpecker: Hallucination Correction for Multimodal Large Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.352798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 889df654-9e6b-438a-bb3b-15c3b94bf55a · outbound

This paper cites MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.360786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82250617-8a53-4ef3-b535-44a5d1d0ca94 · outbound

This paper cites MM-LLMs: Recent Advances in MultiModal Large Language Models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting MM-LLMs: Recent Advances in MultiModal Large Language Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.364204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4416a6ae-448d-4cec-b4e3-263ab76247cc · outbound

This paper cites LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.367873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69c7121d-20b7-4747-9ce3-f3fcf0fe4888 · outbound

This paper cites LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.371298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78aa38a4-f88a-4517-aa7c-0e1b43be75c5 · outbound

This paper cites Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-11T04:29:04.378439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 8a7aceb0-4d08-4cab-bad3-75f05ac9f2c0 · inbound

VLSBench: Unveiling Visual Leakage in Multimodal Safety cites this paper.

VLSBench: Unveiling Visual Leakage in Multimodal Safety RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T05:56:46.433674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7277bf91-625e-450a-a6b9-dc573a7ecbe7 · inbound

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models cites this paper.

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:13:51.539892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06fbccd6-ccf5-4b53-a32f-ac62a3b3c0c9 · inbound

MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs cites this paper.

MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:35:58.091606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a41746f6-c695-405c-87a4-f2817a9eaf7f · inbound

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models cites this paper.

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:15:14.184417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2bf540d-4aa7-4f01-ac6a-db15f91a4cdf · inbound

A Survey on Training-free Alignment of Large Language Models cites this paper.

A Survey on Training-free Alignment of Large Language Models RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T21:18:42.356913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6839cb4a-4f00-4393-a924-a6906d3e6cd1 · inbound

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs cites this paper.

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:35:57.229665Z

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 62fed770-48cb-4f0e-bafa-7a6ca09f30f6 · inbound

When the Defense Writes the Refusal: Auditing Keyword-Scored Evaluation of Inference-Time Defenses for Multimodal Large Language Models cites this paper.

When the Defense Writes the Refusal: Auditing Keyword-Scored Evaluation of Inference-Time Defenses for Multimodal Large Language Models RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T06:17:42.480736Z

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 6182b365-3376-46dd-b98d-d28d04dbe050 · inbound

When the Defense Writes the Refusal: Auditing Keyword-Scored Evaluation of Inference-Time Defenses for Multimodal Large Language Models cites this paper.

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-15T10:53:29.444919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 609026f8-ace2-42ce-ad81-a2ce0c9bcd93 · inbound

When the Defense Writes the Refusal: Auditing Keyword-Scored Evaluation of Inference-Time Defenses for Multimodal Large Language Models cites this paper.

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T11:56:59.624836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09cb3e5f-c354-47c1-89b1-14d8f3458f5e · inbound

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs cites this paper.

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-14T17:33:49.041193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.