Paper Citation Record · LEDGER

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs

As of 8 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 1 inbound Pith citation observation for arXiv:2505.14035.

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

pith.paper-citation-record.v1
2505.14035 v1

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:43:30.875455Z

measured 56 of 56 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T10:39:06.973029Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

55 of 55 outbound references displayed

verified exact2
verified fuzzy11
unresolved40
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation aa3b085a-14e1-4f96-b4d2-4f71b98b07de · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:43:36.416860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b4127d86-3fd7-4d92-93cc-d17579f3350a · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:43:36.232818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d0920203-1927-4f00-90b5-ecc1294bc3bf · outbound

This paper cites 2024.Claude 3.5 Sonnet.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs 2024.Claude 3.5 Sonnet

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:20.984807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30fce836-c84d-49ad-b5a2-aa17f95dee41 · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:43:35.946945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 725c46b1-13f6-4c2e-8568-e3800e343344 · outbound

This paper cites 2023.Azure AI Content Safety.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs 2023.Azure AI Content Safety

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:43:35.787509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b3c4a36a-c6fd-4f32-900e-3005ac7041e9 · outbound

This paper cites 2024.Analyze multimodal content (preview).

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs 2024.Analyze multimodal content (preview)

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:43:35.523027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation df626658-f6ed-4c4a-bed4-d3f9f2746f5b · outbound

This paper cites Qwen2.5-VL Technical Report.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Qwen2.5-VL Technical Report

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:21.494833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 543f4fbe-6505-45ef-b860-2fdf96cef7c5 · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 8

Resolution: verified exact; doi, observed 2026-08-07T15:43:31.610044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fcbff939-49af-4d50-8fd5-c9dad6aed463 · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:21.649314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85dd3af2-21fc-40f7-93d4-a11660d30f97 · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:43:35.344239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 44af8039-f98a-4ca2-9be4-5c51c6071f3a · outbound

This paper cites Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:21.902482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80c8f464-bf6b-422e-9c00-31963e773fe9 · outbound

This paper cites FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicity

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:21.975620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 550239d5-219f-4fde-be5f-5326e9ed6d8a · outbound

This paper cites The Llama 3 Herd of Models.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs The Llama 3 Herd of Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:22.044197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4db1a0a8-41aa-413a-b37b-826705a8e66e · outbound

This paper cites 2024.Fine-Tuned Vision Transformer (ViT) for NSFW Image Classifica- tion.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs 2024.Fine-Tuned Vision Transformer (ViT) for NSFW Image Classifica- tion

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:43:35.167720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f5c46f7f-5bcb-44f7-aaae-1d5af694a8bf · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:43:34.987516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9921580c-44f5-4127-8d69-56bcef3a195c · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:43:34.884018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a3524201-6e34-4f98-af90-8e25ee486686 · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:22.649039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5006dd6c-ca8c-4d1d-9d61-1d8a852d190e · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:43:34.669385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5da19695-0eb1-403b-8fea-7a4dab7db076 · outbound

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

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs VLSBench: Unveiling Visual Leakage in Multimodal Safety

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:22.887756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cccfa9b-1361-422b-be2c-5edeaf6d96aa · outbound

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

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:22.943099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b0bd19c-b116-444f-918f-cada8ced0184 · outbound

This paper cites Tran, Yi Tay, Jeffrey Sorensen, Jai Prakash Gupta, Donald Metzler, and Lucy Vasserman.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Tran, Yi Tay, Jeffrey Sorensen, Jai Prakash Gupta, Donald Metzler, and Lucy Vasserman

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:23.001308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfc50c65-4f3a-4f58-b675-dd7b29a49c81 · outbound

This paper cites GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:23.117182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f289353-924b-4ccc-a971-94161f3934a3 · outbound

This paper cites Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:43:34.412706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 251690df-9200-4b5f-a822-b18e0b3881e9 · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:43:34.212599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 96b4a53e-7e61-4b57-b1d1-e6bdf36e019e · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 25

Resolution: malformed identifier; no resolver link, observed 2026-08-07T15:43:23.440676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe3e2598-759c-4d51-8c67-ebc43eaeee2a · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:23.526490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56721e59-a533-4ec6-8678-82c54d52f987 · outbound

This paper cites LongSafety: Evaluating Long-Context Safety of Large Language Models.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs LongSafety: Evaluating Long-Context Safety of Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:23.665972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57d03572-75d9-4f05-bbdc-1bc53e781700 · outbound

This paper cites JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:23.733760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b1f157b-93b9-436e-9a19-63babe6fa67e · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:23.834745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e3584d2-4709-4043-8ac3-61404fd2b3b7 · outbound

This paper cites 2024.Llama 3 ˙2: Revolutionizing edge AI and vision with open, customizable models.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs 2024.Llama 3 ˙2: Revolutionizing edge AI and vision with open, customizable models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:43:34.050094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 67690c18-0805-47d1-adfa-fca4f97fb705 · outbound

This paper cites Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:24.185429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd6f449c-1a86-415f-a022-dce9ea6bc2d7 · outbound

This paper cites Sy, Ahmad Albunni, Myles Joshua Toledo Tan, and Nouar Aldahoul.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Sy, Ahmad Albunni, Myles Joshua Toledo Tan, and Nouar Aldahoul

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:43:33.884121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4c05969a-269d-47b7-8d61-2b1417e138b0 · outbound

This paper cites 2024.GPT-4o system card.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs 2024.GPT-4o system card

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:43:33.728865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ed041c3e-f2cf-4e5d-b0b2-50cfd2ad207e · outbound

This paper cites 2024.GPT-4V(ision) system card.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs 2024.GPT-4V(ision) system card

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:43:33.541457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fd163384-b867-4f3d-b33d-945f7e5c2f93 · outbound

This paper cites 2024.Moderate images and text.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs 2024.Moderate images and text

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:43:33.342003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7c440e22-6d3d-4a4f-9c6f-5dce709183dc · outbound

This paper cites 2025.Qwen2.5-VL-7B-Instruct.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs 2025.Qwen2.5-VL-7B-Instruct

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:43:33.083387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6806964a-e1de-4920-815d-65d3d27a9bf3 · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:24.954780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aafcd2e3-48d9-4288-90a1-d00e2834db3e · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:25.205302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9203d1f4-63b2-4295-bffb-2000749da03c · outbound

This paper cites Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:25.330017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 433fa097-d213-4c0f-bff8-691facd3af8b · outbound

This paper cites ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:25.490453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85cda172-1a1c-450b-be0b-c4ff775ac396 · outbound

This paper cites ICM-Assistant: Instruction-tuning Multimodal Large Language Models for Rule-based Explainable Image Content Moderation.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs ICM-Assistant: Instruction-tuning Multimodal Large Language Models for Rule-based Explainable Image Content Moderation

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:25.574744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 878436b6-6d4e-4c37-a2d7-07433c4ef039 · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:25.682269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82a9c020-e63c-4abf-88b7-b61b2b15d564 · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:43:32.850079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation db8e43c1-8d1c-4f4e-b447-094fc7764e95 · outbound

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

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs ShieldGemma: Generative AI Content Moderation Based on Gemma

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:25.899451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83c036a9-1752-4c5d-9d45-0ad72cb60093 · outbound

This paper cites SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:26.196963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83b50b0b-f2a9-4768-bb03-133b17228616 · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:30.105067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3be23998-a3b0-48e8-a0ce-4d26b564287d · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:43:32.626116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 190cf86f-ed18-49fa-a2df-e91359ad62d0 · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 48

Resolution: malformed identifier; no resolver link, observed 2026-08-07T15:43:30.354823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6209e798-1471-4f07-a068-41234cb1933f · outbound

This paper cites Multimodal Situational Safety.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Multimodal Situational Safety

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:30.464795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fbe83a9-2a4b-4271-a0bb-906015e7ec21 · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:43:32.392128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cddb65d7-9410-4671-ae2a-d998c97ad791 · outbound

This paper cites an unresolved cited work.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:43:32.165019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 115e824c-f005-41c3-98e3-11e94249d6ec · outbound

This paper cites InThe Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs InThe Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:43:31.933095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 914293f0-9370-4431-9a8c-98c1414c4b12 · outbound

This paper cites InFindings of the Association for Computational Linguistics: ACL 2023.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs InFindings of the Association for Computational Linguistics: ACL 2023

Reference 2023

Resolution: verified exact; doi, observed 2026-08-07T15:43:31.138044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 553144f0-55aa-4cc2-913a-7c5a9c7d1345 · outbound

This paper cites AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:22.394650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4fb3a25-8f12-490e-8323-e4211ad2bab6 · outbound

This paper cites Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails.

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T15:43:22.581145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 6d1e7ba7-cad4-4879-9ad8-731b0aedec7d · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs

Reference 132

Resolution: unresolved; no resolver link, observed 2026-08-05T10:39:06.973029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.