Large vision-language models (LVLMs) have recently dramatically pushed the state of the art in image captioning and many image understanding tasks (e.g., visual question answering). LVLMs, however, often \textit{hallucinate} and produce captions that mention concepts that cannot be found in the image. These hallucinations erode the trustworthiness of LVLMs and are arguably among the main obstacles to their ubiquitous adoption. Recent work suggests that addition of grounding objectives -- those that explicitly align image regions or objects to text spans -- reduces the amount of LVLM hallucination. Although intuitive, this claim is not empirically justified as the reduction effects have been established, we argue, with flawed evaluation protocols that (i) rely on data (i.e., MSCOCO) that has been extensively used in LVLM training and (ii) measure hallucination via question answering rather than open-ended caption generation. In this work, in contrast, we offer the first systematic analysis of the effect of fine-grained object grounding on LVLM hallucination under an evaluation protocol that more realistically captures LVLM hallucination in open generation. Our extensive experiments over three backbone LLMs reveal that grounding objectives have little to no effect on object hallucination in open caption generation.
Detecting Clinical Hallucinations in LVLMs via Counterfactual Visual Grounding Uncertainty
School of Intelligent Science and Technology, Nanjing University（南京大学智能科学与技术学院）；National Institute of Healthcare Data Science at Nanjing University（南京大学医疗数据科学国家研究院）；School of Biomedical Engineering, Nanjing University（南京大学生物医学工程学院）
Grounding or Guessing? Visual Signals for Detecting Hallucinations in Sign Language Translation
German Research Center for Artificial Intelligence (DFKI GmbH)（德国人工智能研究中心（DFKI GmbH））；Saarland Informatics Campus（萨尔兰州信息学校园）；Barcelona Supercomputing Center (BSC-CNS)（巴塞罗那超级计算中心（BSC-CNS））
Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
Hanoi University of Science and Technology（河内科技大学）；Australian Institute for Machine Learning, University of Adelaide（澳大利亚机器学习研究所，阿德莱德大学）；Nanjing University（南京大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Hanoi-Amsterdam High School for the Gifted（河内阿姆斯特丹天才高中）
Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing
School of Computer Science, Wuhan University, China（武汉大学计算机学院）；Zhongguancun Academy, China（中关村学院）；School of Computer Science, Chongqing University, China（重庆大学计算机学院）
