Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-17T22:29:36.960961Z
Paper Citation Record · LEDGER
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models
As of 13 August 2026, this Paper Citation Record lists 78 of 78 outbound references and 3 inbound Pith citation observations for arXiv:2511.10287.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-02T02:44:16.755987Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-02T17:27:14.956941Z
Reference resolution
78 of 78 outbound references displayed
- verified exact23
- verified fuzzy52
- unresolved2
- parse uncertain1
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 545088ee-9011-4783-861f-f3209b9fe15d · outbound
This paper cites an unresolved cited work.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Unresolved cited work
Reference 1
- Resolution
- unresolved
- raw_fallback, observed 2026-05-17T22:30:23.615677Z
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 67d161cc-e878-4da4-9875-e3a76ccbb242 · outbound
This paper cites Meet claude, your thinking partner.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Meet claude, your thinking partner
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.602024Z
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 c2fc2b58-d671-4fe2-803e-fe973b1bb454 · outbound
This paper cites Doubao 1.5 pro: Api pricing & how to use doubao- 1.5-pro api.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Doubao 1.5 pro: Api pricing & how to use doubao- 1.5-pro api
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.599684Z
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 9350da11-2342-47f5-9208-873b5e72b1bb · outbound
This paper cites Qwen Technical Report.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Qwen Technical Report
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T22:30:23.283600Z
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 322959a1-b5ac-4d13-8dfe-9c690e9dc102 · outbound
This paper cites Introducing pcl-baidu wenxin (ernie 3.0 ti- tan), the world’s first knowledge enhanced multi-hundred- billion model.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Introducing pcl-baidu wenxin (ernie 3.0 ti- tan), the world’s first knowledge enhanced multi-hundred- billion model
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.604392Z
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 5b50bdfe-b856-43ad-aace-7504aa9a4dfe · outbound
This paper cites A Cross-Modal Approach to Silent Speech with LLM-Enhanced Recognition.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models A Cross-Modal Approach to Silent Speech with LLM-Enhanced Recognition
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:30:23.280520Z
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 dfc5f065-f81d-4bf2-9fa5-81d648d9e70a · outbound
This paper cites Murder without redress-the need for new legal solutions in the age of character-ai (cai).Avail- able at SSRN 5107942.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Murder without redress-the need for new legal solutions in the age of character-ai (cai).Avail- able at SSRN 5107942
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.606593Z
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 70597037-a1a0-4065-a1d0-cce541816cd3 · outbound
This paper cites Suppression of acoustic noise in speech us- ing spectral subtraction.IEEE Transactions on acoustics, speech, and signal processing, 27(2):113–120.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Suppression of acoustic noise in speech us- ing spectral subtraction.IEEE Transactions on acoustics, speech, and signal processing, 27(2):113–120
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.597225Z
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 ad478650-8f62-447d-bfe0-dae4e48f6501 · outbound
This paper cites ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T22:30:23.286668Z
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 427ab5e3-e48b-49de-9828-4484fa4d2808 · outbound
This paper cites Icdar 2019 robust reading challenge on scanned receipts ocr and information extraction.Web link: https://rrc.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Icdar 2019 robust reading challenge on scanned receipts ocr and information extraction.Web link: https://rrc
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.618263Z
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 120d8ccb-a6e9-43a6-b27c-786c1fa9b044 · outbound
This paper cites Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges
Reference 11
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:30:23.277475Z
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 0d00c9ef-8190-41a5-b2c9-9a45c9c529d4 · outbound
This paper cites Hatemm: A multi- modal dataset for hate video classification.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Hatemm: A multi- modal dataset for hate video classification
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.611261Z
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 9b022462-54a5-437b-94ad-c07833bb2f7f · outbound
This paper cites The pascal visual object classes (voc) challenge.International journal of computer vision, 88:303–338.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models The pascal visual object classes (voc) challenge.International journal of computer vision, 88:303–338
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.613678Z
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 053fec9f-3bea-4633-9b5e-dfa6fc320e8b · outbound
This paper cites guided mllm reasoning: Enhancing mllm with knowledge and visual notes for visual question answering.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models guided mllm reasoning: Enhancing mllm with knowledge and visual notes for visual question answering
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.609022Z
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 af544a11-ca92-4b35-afd6-4d48996ca1d5 · outbound
This paper cites Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:30:23.211554Z
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 0ca0d029-9808-42bd-8993-93559f010943 · outbound
This paper cites Find any sound you like.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Find any sound you like
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.493611Z
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 05a88bb0-9530-4eb5-a1c1-3a09a9defdbe · outbound
This paper cites an unresolved cited work.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Unresolved cited work
Reference 17
- Resolution
- parse uncertain
- raw_fallback, observed 2026-05-17T22:30:23.525133Z
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 44ecccc0-0f8c-488c-8687-1fef96871477 · outbound
This paper cites Gemini: Our most intelligent ai models.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Gemini: Our most intelligent ai models
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.527165Z
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 52909e12-401b-468a-a600-2ca20dd23176 · outbound
This paper cites Mllmguard: A multi-dimensional safety evalua- tion suite for multimodal large language models.Advances in Neural Information Processing Systems, 37:7256–7295.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Mllmguard: A multi-dimensional safety evalua- tion suite for multimodal large language models.Advances in Neural Information Processing Systems, 37:7256–7295
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.591955Z
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 b1c77cfb-29a2-410c-9b66-b875850e17d2 · outbound
This paper cites A large-scale comprehensive dataset and copy-overlap aware evaluation protocol for segment-level video copy detection.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models A large-scale comprehensive dataset and copy-overlap aware evaluation protocol for segment-level video copy detection
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.511673Z
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 b39721ac-9924-46db-b516-08cc611bf8d9 · outbound
This paper cites Deepfake detection using deep learning meth- ods: A systematic and comprehensive review.Wiley Interdis- ciplinary Reviews: Data Mining and Knowledge Discovery, 14(2):e1520.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Deepfake detection using deep learning meth- ods: A systematic and comprehensive review.Wiley Interdis- ciplinary Reviews: Data Mining and Knowledge Discovery, 14(2):e1520
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.556321Z
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 6211f762-6bbb-4761-ba08-4cbf70b0d8dd · outbound
This paper cites Gpt-4o: The cutting-edge advancement in multimodal llm.Authorea Preprints.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Gpt-4o: The cutting-edge advancement in multimodal llm.Authorea Preprints
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.531686Z
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 739972c1-18f7-4de9-925d-a0f891d4380f · outbound
This paper cites Funsd: A dataset for form understanding in noisy scanned documents.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Funsd: A dataset for form understanding in noisy scanned documents
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.502430Z
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 4afea782-c61d-43ee-947f-e1392bf7c0ee · outbound
This paper cites Swsr: A chinese dataset and lexicon for online sexism detec- tion.Online Social Networks and Media, 27:100182.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Swsr: A chinese dataset and lexicon for online sexism detec- tion.Online Social Networks and Media, 27:100182
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.523077Z
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 2c113c21-f5cd-499d-ad72-e76bf07d0374 · outbound
This paper cites Fairface: Face attribute dataset for balanced race, gender, and age for bias measurement and mitigation.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Fairface: Face attribute dataset for balanced race, gender, and age for bias measurement and mitigation
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.568271Z
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 98699c35-12a6-495d-801c-589c964020b3 · outbound
This paper cites PRIV-QA: Privacy-Preserving Question Answering for Cloud Large Language Models.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models PRIV-QA: Privacy-Preserving Question Answering for Cloud Large Language Models
Reference 26
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:30:23.264889Z
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 169c5edd-943f-45e4-937a-6a768a8a5ca2 · outbound
This paper cites Col- laborative evaluation: Exploring the synergy of large lan- guage models and humans for open-ended generation eval- uation.arXiv e-prints, pages arXiv–2310.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Col- laborative evaluation: Exploring the synergy of large lan- guage models and humans for open-ended generation eval- uation.arXiv e-prints, pages arXiv–2310
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.495786Z
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 d8facfe0-c78c-4076-8fc1-ca919cf5a694 · outbound
This paper cites PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations
Reference 28
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:30:23.220898Z
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 341f8510-3cea-4988-989c-c88264d18016 · outbound
This paper cites Rule-based data selection for large language mod- els.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Rule-based data selection for large language mod- els
Reference 29
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:30:23.255484Z
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 86caa8fe-162d-4fb6-ad5a-432c8a91de85 · outbound
This paper cites Mcfend: A multi-source benchmark dataset for chinese fake news de- tection.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Mcfend: A multi-source benchmark dataset for chinese fake news de- tection
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.504854Z
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 188ac597-16b6-4ce8-b2f9-11e8718ccef4 · outbound
This paper cites LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models
Reference 31
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:30:23.267894Z
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 44b7f6b5-befc-4a3f-b9d5-4c2609bace60 · outbound
This paper cites DeepSeek-V3 Technical Report.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models DeepSeek-V3 Technical Report
Reference 32
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T22:30:23.194479Z
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 81dd585a-bf5e-4972-b1aa-339f9e7480ed · outbound
This paper cites Mm-safetybench: A benchmark for safety eval- uation of multimodal large language models.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Mm-safetybench: A benchmark for safety eval- uation of multimodal large language models
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.573664Z
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 950c5bdf-9ef4-480c-928b-a72663570ea8 · outbound
This paper cites G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T22:30:23.214656Z
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 55380fa7-9fa9-4b1c-b990-133244ef57da · outbound
This paper cites Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Reference 35
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T22:30:23.271111Z
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 7605bdb1-3a8b-4a27-ac1f-4a6f092cf6d6 · outbound
This paper cites Pv-vtt: A privacy-centric dataset for mission- specific anomaly detection and natural language interpreta- tion.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Pv-vtt: A privacy-centric dataset for mission- specific anomaly detection and natural language interpreta- tion
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.594395Z
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 1c10f3f5-0245-4ccb-8b8e-6db5c1f5238d · outbound
This paper cites Ethos: a multi-label hate speech de- tection dataset.Complex & Intelligent Systems, 8(6):4663– 4678.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Ethos: a multi-label hate speech de- tection dataset.Complex & Intelligent Systems, 8(6):4663– 4678
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.536166Z
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 420d837a-209c-4bfd-9fd3-4b05dd16030b · outbound
This paper cites Detecting potential violent be- havior using deep learning.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Detecting potential violent be- havior using deep learning
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.500090Z
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 d4be4337-c3df-4f26-9bef-f00021ce0cf8 · outbound
This paper cites BBQ: A Hand-Built Bias Benchmark for Question Answering.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models BBQ: A Hand-Built Bias Benchmark for Question Answering
Reference 39
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T22:30:23.261552Z
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 05c04b6c-4f38-417b-889e-5a5dac4de612 · outbound
This paper cites Fakesv: A multi- modal benchmark with rich social context for fake news de- tection on short video platforms.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Fakesv: A multi- modal benchmark with rich social context for fake news de- tection on short video platforms
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.547078Z
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 44d68da1-b45e-4ec9-94fb-ea9daa82f868 · outbound
This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
Reference 41
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T22:30:23.217680Z
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 79e9197d-ba8b-460e-84ca-5c8346ac9114 · outbound
This paper cites Fine-tuning aligned language models compromises safety, even when users do not intend to!.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Fine-tuning aligned language models compromises safety, even when users do not intend to!
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.518524Z
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 49beb48a-a0ad-4f02-a877-349e65cc76c0 · outbound
This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reference 43
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T22:30:23.274048Z
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 9a8c8a0e-b6e4-4fdb-a378-be689fafc80b · outbound
This paper cites AudioSet.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models AudioSet
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.577965Z
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 ac57f132-57fe-4758-bbb3-fd853ff37429 · outbound
This paper cites Hate speech detection in the bengali lan- guage: A dataset and its baseline evaluation.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Hate speech detection in the bengali lan- guage: A dataset and its baseline evaluation
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.497991Z
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 b120e03f-5ea0-45cc-a226-56db728611d3 · outbound
This paper cites Who validates the validators? aligning llm-assisted evaluation of llm outputs with human preferences.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Who validates the validators? aligning llm-assisted evaluation of llm outputs with human preferences
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.520852Z
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 6a834ebf-f028-476f-9414-5413cb46c7ce · outbound
This paper cites Overview of ccl23-eval task 8: Chinese essay fluency eval- uation (cefe) task.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Overview of ccl23-eval task 8: Chinese essay fluency eval- uation (cefe) task
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.570498Z
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 52e45f61-fbdf-4c68-b3a1-feb0668bcf1f · outbound
This paper cites Real-world anomaly detection in surveillance videos.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Real-world anomaly detection in surveillance videos
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.575961Z
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 e76d5fb2-16a1-448c-bb15-c5009ce07ae8 · outbound
This paper cites Case-bench: Context-aware safety bench- mark for large language models.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Case-bench: Context-aware safety bench- mark for large language models
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.582582Z
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 a7af2d15-d6fc-4dd6-a899-7e1ad6a5ae9e · outbound
This paper cites Safety Assessment of Chinese Large Language Models.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Safety Assessment of Chinese Large Language Models
Reference 50
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:30:23.201586Z
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 e752d3d0-1aee-489e-b3ed-8273c6d81d6f · outbound
This paper cites TrustLLM: Trustworthiness in Large Language Models.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models TrustLLM: Trustworthiness in Large Language Models
Reference 51
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T11:17:09.209714Z
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 766de1cf-41aa-4c03-afc6-01e9e0a3558c · outbound
This paper cites Gemini: A Family of Highly Capable Multimodal Models.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Gemini: A Family of Highly Capable Multimodal Models
Reference 52
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T22:30:23.208099Z
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 b049805a-607b-4e8f-b383-367b4963bad0 · outbound
This paper cites How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
Reference 53
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:30:23.252260Z
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 c5fc44d4-d30d-4ff2-8a91-d6e7e1c8669a · outbound
This paper cites A study on integrating machine learning tech- niques for waste management.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models A study on integrating machine learning tech- niques for waste management
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.560795Z
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 3aae70bb-99d7-440a-8d2f-55425963be5c · outbound
This paper cites Belgian man dies by suicide following ex- changes with chatbot.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Belgian man dies by suicide following ex- changes with chatbot
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.587137Z
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 ce015680-0e26-47a9-b530-9c452d7c4915 · outbound
This paper cites Pdid: database of molecular-level puta- tive protein–drug interactions in the structural human pro- teome.Bioinformatics, 32(4):579–586.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Pdid: database of molecular-level puta- tive protein–drug interactions in the structural human pro- teome.Bioinformatics, 32(4):579–586
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.565767Z
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 f00c0a4e-4693-45ca-84dc-4d9abf9371eb · outbound
This paper cites Multihateclip: A multilingual benchmark dataset for hateful video detection on youtube and bilibili.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Multihateclip: A multilingual benchmark dataset for hateful video detection on youtube and bilibili
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.589534Z
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 8946c779-439d-4130-9f71-9b90eae31c70 · outbound
This paper cites Cnn-generated images are surprisingly easy to spot.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Cnn-generated images are surprisingly easy to spot
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.584837Z
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 248c1832-0d7b-43f0-b770-5ed93f46fbc8 · outbound
This paper cites Multimodal llm enhanced cross- lingual cross-modal retrieval.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Multimodal llm enhanced cross- lingual cross-modal retrieval
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.580219Z
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 5de3b0d0-f0ff-49d9-b094-31d3cb50b857 · outbound
This paper cites Safebench: A benchmarking platform for safety evaluation of autonomous vehicles.Advances in Neural Information Processing Systems, 35:25667–25682.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Safebench: A benchmarking platform for safety evaluation of autonomous vehicles.Advances in Neural Information Processing Systems, 35:25667–25682
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.554063Z
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 37fcecaa-d9bc-4211-ae45-036e9db1a56e · outbound
This paper cites Lvlm-ehub: A comprehensive evaluation benchmark for large vision-language models.IEEE Transactions on Pat- tern Analysis and Machine Intelligence.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Lvlm-ehub: A comprehensive evaluation benchmark for large vision-language models.IEEE Transactions on Pat- tern Analysis and Machine Intelligence
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.544701Z
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 6fc15024-0c61-4aa2-9ddf-8c353335db91 · outbound
This paper cites LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
Reference 62
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:30:23.197949Z
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 d8188977-9b7f-41a6-9ba6-45ddc0e9fdd8 · outbound
This paper cites Lamm: Language-assisted multi- modal instruction-tuning dataset, framework, and bench- mark.Advances in Neural Information Processing Systems, 36:26650–26685.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Lamm: Language-assisted multi- modal instruction-tuning dataset, framework, and bench- mark.Advances in Neural Information Processing Systems, 36:26650–26685
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.509422Z
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 01baa8ea-d060-4c0f-8009-3b53ebd1fc81 · outbound
This paper cites an unresolved cited work.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Unresolved cited work
Reference 64
- Resolution
- unresolved
- raw_fallback, observed 2026-05-17T22:30:23.540294Z
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 6dd6879e-960f-41ff-b8b4-b7032ffe2f96 · outbound
This paper cites Timesuite: Improving mllms for long video understanding via grounded tuning.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Timesuite: Improving mllms for long video understanding via grounded tuning
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.533914Z
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 d75cc30b-9f41-49de-9bc9-59e7826bc537 · outbound
This paper cites Exo2ego: Exocentric knowledge guided mllm for egocentric video understanding.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Exo2ego: Exocentric knowledge guided mllm for egocentric video understanding
Reference 66
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:30:23.204881Z
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 f6e31873-1ee6-463e-afd2-a6992fca8476 · outbound
This paper cites Differential-perceptive and retrieval- augmented mllm for change captioning.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Differential-perceptive and retrieval- augmented mllm for change captioning
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.529528Z
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 7a598fdc-efba-4daa-b5c0-c15f8c30046e · outbound
This paper cites Multitrust: A comprehensive bench- mark towards trustworthy multimodal large language mod- els.Advances in Neural Information Processing Systems, 37:49279–49383.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Multitrust: A comprehensive bench- mark towards trustworthy multimodal large language mod- els.Advances in Neural Information Processing Systems, 37:49279–49383
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.558564Z
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 656485e0-10b7-4be0-9511-396446ca99ff · outbound
This paper cites Efficient motion-aware video mllm.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Efficient motion-aware video mllm
Reference 69
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.549207Z
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 3cbec8e2-f604-4261-bde9-11cf86bdb1ff · outbound
This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623
Reference 70
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.507179Z
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 c955c24a-2855-41f8-ab71-0f3a52fd07ec · outbound
This paper cites Image-based table recognition: data, model, and evaluation.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Image-based table recognition: data, model, and evaluation
Reference 71
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.538345Z
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 c5303516-bf73-4f80-9788-71367453667c · outbound
This paper cites Places: A 10 million image database for scene recognition.IEEE transactions on pattern analysis and machine intelligence, 40(6):1452–1464.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Places: A 10 million image database for scene recognition.IEEE transactions on pattern analysis and machine intelligence, 40(6):1452–1464
Reference 72
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.563421Z
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 7f35fc20-bda6-4e44-98d3-5ff8b45fc560 · outbound
This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Reference 73
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T22:30:23.224376Z
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 58a719bb-ecbb-4d06-aa27-1a54607dc3bd · outbound
This paper cites A detailed break- down of the dataset sources and their corresponding content domains is presented in Table 5.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models A detailed break- down of the dataset sources and their corresponding content domains is presented in Table 5
Reference 74
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.542613Z
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 c5d2c4f8-04da-4427-be11-ec53d09776a5 · outbound
This paper cites role": "system.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models role": "system
Reference 75
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.516163Z
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 585544d9-4b99-40e4-a5da-b8ba850e5650 · outbound
This paper cites Privacy and Property.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Privacy and Property
Reference 76
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.513991Z
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 42037712-91de-47b6-bed5-7e37dfef8bce · outbound
This paper cites This subset covers balanced distributions across nine risk categories and four modalities (text, image, audio and video), with detailed data shown in the table 4.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models This subset covers balanced distributions across nine risk categories and four modalities (text, image, audio and video), with detailed data shown in the table 4
Reference 77
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T22:30:23.551964Z
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 b5666f61-8bfa-479a-8826-12c0d12d6b6b · outbound
This paper cites an unresolved cited work.
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models Unresolved cited work
Reference 78
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:30:23.258567Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Pith citing papers
Observation fed8506a-f643-4fc8-98cf-1dbb98905cbc · inbound
VoxSafeBench: Not Just What Is Said, but Who, How, and Where cites this paper.
VoxSafeBench: Not Just What Is Said, but Who, How, and Where OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models
Reference 62
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T10:24:22.003486Z
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 0a0e02a2-eef3-42e0-b8d8-1f226f359c8b · inbound
Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMs cites this paper.
Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMs OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models
Reference 47
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T17:27:14.958299Z
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 9921a8aa-53d0-4ed6-8c6d-f66a804b1077 · inbound
Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation cites this paper.
Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T02:44:16.755987Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.