Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs
School of Computing and Information Systems, Singapore Management University(新加坡管理大学计算与信息系统学院);Institute of Operations Research and Analytics, National University of Singapore(新加坡国立大学运筹学与分析研究所)
Detecting multimodal misinformation, especially in the form of image-text pairs, is crucial. Obtaining large-scale, high-quality real-world fact-checking datasets for training detectors is costly, leading researchers to use synthetic datasets generated by AI technologies. However, the generalizability of detectors trained on synthetic data to real-world scenarios remains unclear due to the distribution gap. To address this, we propose learning from synthetic data for detecting real-world multimodal misinformation through two model-agnostic data selection methods that match synthetic and real-world data distributions. Experiments show that our method enhances the performance of a small MLLM (13B) on real-world fact-checking datasets, enabling it to even surpass GPT-4V~\cite{GPT-4V}.
Insight-A: Attribution-aware for Multimodal Misinformation Detection
School of Computer Science and Technology, Soochow University(苏州大学计算机科学与技术学院);Institute of Artificial Intelligence, Soochow University(苏州大学人工智能研究院);School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院)
SpMis: An Investigation of Synthetic Spoken Misinformation Detection
The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Northeastern University(东北大学);Beijing Institute of Technology(北京理工大学);Huawei International Pte Ltd(华为国际私人有限公司);Huawei Technologies Co., Ltd(华为技术有限公司)
MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs
Beijing University of Posts and Telecommunications(北京邮电大学);University of California, Santa Barbara(加州大学圣巴巴拉分校);Center for Research on Intelligent Perception and Computing, NLPR, CASIA(中国科学院自动化研究所模式识别国家重点实验室智能感知与计算研究中心)
Harmfully Manipulated Images Matter in Multimodal Misinformation Detection
Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education, Jilin University(吉林大学 教育部符号计算与知识工程重点实验室);College of Computer Science and Technology, Jilin University(吉林大学 计算机科学与技术学院)
College of Computer Science and Technology, Jilin University(吉林大学计算机科学与技术学院);College of Software, Jilin University(吉林大学软件学院);School of Computer and Artificial Intelligence, Liaoning Normal University(辽宁师范大学计算机与人工智能学院);School of Computer Science and Technology, Soochow University(苏州大学计算机科学与技术学院);Department of Computer Science, Swansea University(斯旺西大学计算机科学系)
HiEAG: Evidence-Augmented Generation for Out-of-Context Misinformation Detection
School of Computer Science and Technology, Soochow University(苏州大学计算机科学与技术学院);Institute of Artificial Intelligence, Soochow University(苏州大学人工智能研究院);School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学计算机科学与技术学院)
Echoes of Unrest: A Multimodal NLP Framework for Early Warning of Fake News and Violence-Driven Mob Activity
Department of Computer Science and Engineering, Dhaka International University(达卡国际大学计算机科学与工程系);Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology(孟加拉国工程技术大学计算机科学与工程系)
E-CaTCH: Event-Centric Cross-Modal Attention with Temporal Consistency and Class-Imbalance Handling for Misinformation Detection
Department of Mathematics and Statistics, American University, Washington, DC, USA(数学与统计学系,美国大学,华盛顿特区,美国);Department of Computer Science and Mathematics, Pennsylvania State University, Harrisburg, PA, USA(计算机科学与数学系,宾夕法尼亚州立大学,哈里斯堡,宾夕法尼亚州,美国);Department of Computer Science, American University, Washington, DC, USA(计算机科学系,美国大学,华盛顿特区,美国)
MIC: Explaining Image-Claim Inconsistencies in AI-Generated Multimodal Misinformation
KU Leuven(鲁汶大学);TU Darmstadt(达姆施塔特工业大学);National Research Center for Applied Cybersecurity ATHENE(国家应用网络安全研究中心ATHENE);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs
The University of Texas at Austin(德克萨斯大学奥斯汀分校);Pennsylvania State University(宾夕法尼亚州立大学);New York University(纽约大学);University of Chinese Academy of Sciences(中国科学院大学);AG2ai, Inc.(AG2ai公司)
OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models
Harbin Institute of Technology(哈尔滨工业大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));BIAI, ZJUT & D5Data.ai(BIAI、浙江工业大学及D5Data.ai);National University of Singapore(新加坡国立大学)
Customized large language models can outperform Community Notes in correcting misinformation
Paul G. Allen School of Computer Science and Engineering, University of Washington(保罗·G·阿伦计算机科学与工程学院,华盛顿大学);Computer Science Department, Boise State University(计算机科学系,博伊西州立大学);Microsoft Corporation(微软公司)
Visual Authority and the Rhetoric of Health Misinformation: A Multimodal Analysis of Social Media Videos
School of Computer Science(计算机科学学院);Carleton University(卡尔顿大学);Department of Law and Legal Studies(法律与法律研究系);School of Journalism and Communication(新闻与传播学院)
How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models
Seoul National University(首尔大学);Samaya AI;Allen Institute for AI(艾伦人工智能研究所);Yonsei University(延世大学);Carnegie Mellon University(卡内基梅隆大学);University of Washington(华盛顿大学);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);New York University(纽约大学)
Edited Media Understanding Frames: Reasoning About the Intent and Implications of Visual Misinformation
Allen Institute for Artificial Intelligence(艾伦人工智能研究所);University of Michigan(密歇根大学);Paul G. Allen School of Computer Science & Engineering, University of Washington(华盛顿大学保罗·G·艾伦计算机科学与工程学院);Stanford University(斯坦福大学)