Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models
University of Electronic Science and Technology of China(电子科技大学);Southern University of Science and Technology(南方科技大学);University of Birmingham(伯明翰大学);The University of Hong Kong(香港大学)
Qingni Wang, Tiantian Geng, Zhiyuan Wang, Teng Wang, Bo Fu, Feng Zheng
Multimodal Large Language Models (MLLMs) exhibit promising advancements across various tasks, yet they still encounter significant trustworthiness issues. Prior studies apply Split Conformal Prediction (SCP) in language modeling to construct prediction sets with statistical guarantees. However, these methods typically rely on internal model logits or are restricted to multiple-choice settings, which hampers their generalizability and adaptability in dynamic, open-ended environments. In this paper, we introduce TRON, a two-step framework for risk control and assessment, applicable to any MLLM that supports sampling in both open-ended and closed-ended scenarios. TRON comprises two main components: (1) a novel conformal score to sample response sets of minimum size, and (2) a nonconformity score to identify high-quality responses based on self-consistency theory, controlling the error rates by two specific risk levels. Furthermore, we investigate semantic redundancy in prediction sets within open-ended contexts for the first time, leading to a promising evaluation metric for MLLMs based on average set size. Our comprehensive experiments across four Video Question-Answering (VideoQA) datasets utilizing eight MLLMs show that TRON achieves desired error rates bounded by two user-specified risk levels. Additionally, deduplicated prediction sets maintain adaptiveness while being more efficient and stable for risk assessment under different risk levels.
Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
Sun Yat-Sen University(中山大学);Zhejiang University(浙江大学);BraneMatrix AI;Nanyang Technological University(南洋理工大学);Alibaba Group(阿里巴巴集团);Renmin University of China(中国人民大学)
MMRQA: Signal-Enhanced Multimodal Large Language Models for MRI Quality Assessment
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(深圳先进技术研究院,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);ShanghaiTech University(上海理工大学);Southern University of Science and Technology(南方科技大学)
FLEX: A Largescale Multimodal, Multiview Dataset for Learning Structured Representations for Fitness Action Quality Assessment
School of Biomedical Engineering (Suzhou), USTC(中国科学技术大学苏州生物医学工程学院);Suzhou Institute of Biomedical Engineering and Technology, CAS(中国科学院苏州生物医学工程技术研究所);Institute of High-Performance Computing, A*STAR, Singapore(新加坡科技研究局高性能计算研究所);School of Psychology, Beijing Sports University(北京体育大学心理学院);School of Competitive Sports, Beijing Sports University(北京体育大学竞技体育学院);Department of Robotics, University of Michigan(密歇根大学机器人系)
Enhancing Zero-shot Personalized Image Aesthetics Assessment with Profile-aware Multimodal LLM
Mashang Consumer Finance Co., Ltd.(马莎消费金融有限公司);Xi'an Jiaotong-Liverpool University(西安交通大学利物浦大学);Beijing University of Posts and Telecommunications(北京邮电大学)