ACL Findings2025
MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models
Bohan Jin, Shuhan Qi, Kehai Chen, Xinyi Guo, Xuan Wang
Abstract
The widespread use of Large Multimodal Models (LMMs) has raised concerns about model toxicity. However, current research mainly focuses on explicit toxicity, with less attention to some more implicit toxicity regarding prejudice and discrimination. To address this limitation, we introduce a subtler type of toxicity named dual-implicit toxicity and a novel toxicity benchmark termed MDIT-Bench: Multimodal Dual-Implicit Toxicity Benchmark. Specifically, we first create the MDIT-Dataset with dual-implicit toxicity using the proposed Multistage Human-in-loop In-context Generation method. Based on this dataset, we construct the MDIT-Bench, a benchmark for evaluating the sensitivity of models to dual-implicit toxicity, with 317,638 questions covering 12 categories, 23 subcategories, and 780 topics. MDIT-Bench includes three difficulty levels, and we propose a metric to measure the toxicity gap exhibited by the model across them. In the experiment, we conducted MDIT-Bench on 13 prominent LMMs, and the results show that these LMMs cannot handle dual-implicit toxicity effectively.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
- Visual Instruction Tuning cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
Builds on13
- Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023 · 11,349 citations
- BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsJunnan Li, Dongxu Li, Silvio Savarese, Steven C. H. HoiICML 2023 · 7,873 citations
- InstructBLIP: Towards General-purpose Vision-Language Models with Instruction TuningWenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong et al.NeurIPS 2023 · 4,013 citations
- RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language ModelsSamuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi et al.EMNLP Findings 2020 · 692 citations
- Many-shot JailbreakingCem Anil, Esin Durmus, Nina Panickssery, Mrinank Sharma et al.NeurIPS 2024 · 338 citations
Related papers
- ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs: ShieldVLMShiyao Cui, Qinglin Zhang, Xuan Ouyang, Renmiao Chen et al.ACM MM 2025 · 3 citations
- ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI ConversationZi Lin, Zihan Wang, Yongqi Tong, Yangkun Wang et al.EMNLP Findings 2023 · 44 citations
- MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn DialoguesZheyuan Liu, Dongwhi Kim, Yixin Wan, Xiangchi Yuan et al.ACL Findings 2026
- ELITE: Enhanced Language-Image Toxicity Evaluation for SafetyWonjun Lee, Doehyeon Lee, Eugene Choi, Sangyoon Yu et al.ICML 2025
- PclGPT: A Large Language Model for Patronizing and Condescending Language DetectionHongbo Wang, Mingda Li, Junyu Lu, Hebin Xia et al.EMNLP Findings 2024 · 3 citations
