中文
相关论文

相关论文: Exposing Hallucinations To Suppress Them: VLMs Rep…

200 篇论文

Multi-modal large language models (MLLMs) have been shown to efficiently integrate natural language with visual information to handle multi-modal tasks. However, MLLMs still face a fundamental limitation of hallucinations, where they tend…

计算机视觉与模式识别 · 计算机科学 2024-02-27 Chaoya Jiang , Haiyang Xu , Mengfan Dong , Jiaxing Chen , Wei Ye , Ming Yan , Qinghao Ye , Ji Zhang , Fei Huang , Shikun Zhang

Hallucinations in vision-language models (VLMs) hinder reliability and real-world applicability, usually stemming from distribution shifts between pretraining data and test samples. Existing solutions, such as retraining or fine-tuning on…

多媒体 · 计算机科学 2025-06-10 Fei Zhao , Chengcui Zhang , Runlin Zhang , Tianyang Wang , Xi Li

Hallucinations in Multimodal Large Language Models (MLLMs) where generated responses fail to accurately reflect the given image pose a significant challenge to their reliability. To address this, we introduce ConVis, a novel training-free…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Yeji Park , Deokyeong Lee , Junsuk Choe , Buru Chang

Multimodal Large Language Models (MLLMs) have garnered significant attention recently and demonstrate outstanding capabilities in various tasks such as OCR, VQA, captioning, $\textit{etc}$. However, hallucination remains a persistent issue.…

计算机视觉与模式识别 · 计算机科学 2025-12-23 Zehao Wang , Xinpeng Liu , Yudonglin Zhang , Xiaoqian Wu , Zhou Fang , Yifan Fang , Junfu Pu , Cewu Lu , Yong-Lu Li

Large Vision-Language Models (LVLMs) integrate image encoders with Large Language Models (LLMs) to process multi-modal inputs and perform complex visual tasks. However, they often generate hallucinations by describing non-existent objects…

计算机视觉与模式识别 · 计算机科学 2025-02-25 Yaqi Sun , Kyohei Atarashi , Koh Takeuchi , Hisashi Kashima

Multimodal Large Language Models often suffer from object hallucination. While existing research utilizes attention enhancement and visual retracing, we find these works lack sufficient interpretability regarding attention drift in final…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Chengxu Yang , Jingling Yuan , Chuang Hu , Jiawei Jiang

While Large Vision-Language Models (LVLMs) have exhibited remarkable capabilities across a wide range of tasks, they suffer from hallucination problems, where models generate plausible yet incorrect answers given the input image-query pair.…

计算机视觉与模式识别 · 计算机科学 2024-08-02 Xiaoye Qu , Mingyang Song , Wei Wei , Jianfeng Dong , Yu Cheng

Although Large Vision-Language Models (LVLMs) have made substantial progress, hallucination, where generated text is not grounded in the visual input, remains a challenge. As LVLMs become stronger, previously reported hallucination…

计算机视觉与模式识别 · 计算机科学 2026-03-03 April Fu

Large Vision-Language Models (LVLMs) are an extension of Large Language Models (LLMs) that facilitate processing both image and text inputs, expanding AI capabilities. However, LVLMs struggle with object hallucinations due to their reliance…

计算与语言 · 计算机科学 2024-08-12 Avshalom Manevich , Reut Tsarfaty

Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language reasoning, yet they remain vulnerable to hallucination, where generated content deviates from visual evidence. Existing mitigation strategies…

计算机视觉与模式识别 · 计算机科学 2026-03-02 Xingyu Zhu , Kesen Zhao , Liang Yi , Shuo Wang , Zhicai Wang , Beier Zhu , Hanwang Zhang

Multimodal Large Language Models (MLLMs) excel in vision-language tasks such as image captioning but remain prone to object hallucinations, where they describe objects that do not appear in the image. To mitigate this, we propose LISA, a…

计算机视觉与模式识别 · 计算机科学 2025-11-14 Zhihui Guo , Xin Man , Hui Xu , Jie Shao , Zhiguo Jiang , Xianchao Zhang , Heng Tao Shen

Large Vision-Language Models (LVLMs) bridge the gap between visual and linguistic modalities, demonstrating strong potential across a variety of domains. However, despite significant progress, LVLMs still suffer from severe hallucination…

计算机视觉与模式识别 · 计算机科学 2025-12-23 Ruiqi Ma , Yu Yan , Chunhong Zhang , Minghao Yin , XinChao Liu , Zhihong Jin , Zheng Hu

Large Vision-Language Models (LVLMs) exhibit powerful generative capabilities but frequently produce hallucinations that compromise output reliability. Fine-tuning on annotated data devoid of hallucinations offers the most direct solution,…

计算机视觉与模式识别 · 计算机科学 2026-04-23 Xingyu Zhu , Junfeng Fang , Shuo Wang , Beier Zhu , Zhicai Wang , Yonghui Yang , Xiangnan He

This paper aims to address the challenge of hallucinations in Multimodal Large Language Models (MLLMs) particularly for dense image captioning tasks. To tackle the challenge, we identify the current lack of a metric that finely measures the…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Cong Chen , Mingyu Liu , Chenchen Jing , Yizhou Zhou , Fengyun Rao , Hao Chen , Bo Zhang , Chunhua Shen

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in multimodal task reasoning. However, they often generate responses that appear plausible yet do not accurately reflect the visual content, a phenomenon known…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Jiaqi Wang , Yifei Gao , Jitao Sang

Multimodal Large Language Models (MLLMs) have demonstrated strong performance in visual understanding tasks, yet they often suffer from object hallucinations--generating descriptions of objects that are inconsistent with or entirely absent…

人工智能 · 计算机科学 2025-05-27 Xinmiao Hu , Chun Wang , Ruihe An , ChenYu Shao , Xiaojun Ye , Sheng Zhou , Liangcheng Li

Despite progress in Large Vision Language Models (LVLMs), object hallucination remains a critical issue in image captioning task, where models generate descriptions of non-existent objects, compromising their reliability. Previous work…

计算机视觉与模式识别 · 计算机科学 2026-04-09 Shiyu Liu , Xinyi Wen , Zhibin Lan , Ante Wang , Jinsong Su

The Large Visual Language Models (LVLMs) enhances user interaction and enriches user experience by integrating visual modality on the basis of the Large Language Models (LLMs). It has demonstrated their powerful information processing and…

人工智能 · 计算机科学 2024-10-22 Wei Lan , Wenyi Chen , Qingfeng Chen , Shirui Pan , Huiyu Zhou , Yi Pan

Generative Vision-Language Models (VLMs) are prone to generate plausible-sounding textual answers that, however, are not always grounded in the input image. We investigate this phenomenon, usually referred to as "hallucination" and show…

Large vision-language models (LVLMs) have demonstrated remarkable multimodal comprehension and reasoning capabilities, but they still suffer from severe object hallucination. Previous studies primarily attribute the flaw to linguistic prior…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Haohan Zheng , Zhenguo Zhang
‹ 上一页 1 2 3 10 下一页 ›