中文
相关论文

相关论文: ViBe: A Text-to-Video Benchmark for Evaluating Hal…

200 篇论文

Recently, multimodal large language models have made significant advancements in video understanding tasks. However, their ability to understand unprocessed long videos is very limited, primarily due to the difficulty in supporting the…

计算机视觉与模式识别 · 计算机科学 2024-06-18 Yiwei Sun , Zhihang Liu , Chuanbin Liu , Bowei Pu , Zhihan Zhang , Hongtao Xie

Object hallucination is a significant challenge that hinders the application of large vision-language models (LVLMs) in practice. We hypothesize that one possible origin of hallucination is the model's tendency to prioritize text generation…

计算机视觉与模式识别 · 计算机科学 2026-05-21 Meng Shen , Minghao Wu , Deepu Rajan

Large vision-language models (LVLMs) often hallucinate content that is fluent yet unsupported by the image, limiting their reliability in real-world deployment. We show that a key failure mode arises from route competition: even when visual…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Zhe Cheng , Wenyu Chen , Fode Zhang , Dehuan Shen

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

Vision-language models (VLMs) now rival human performance on many multimodal tasks, yet they still hallucinate objects or generate unsafe text. Current hallucination detectors, e.g., single-token linear probing (LP) and PTrue, typically…

人工智能 · 计算机科学 2025-10-22 Geigh Zollicoffer , Minh Vu , Manish Bhattarai

Despite their impressive capabilities, multimodal large language models (MLLMs) are prone to hallucinations, i.e., the generated content that is nonsensical or unfaithful to input sources. Unlike in LLMs, hallucinations in MLLMs often stem…

计算机视觉与模式识别 · 计算机科学 2025-05-09 Xin Zou , Yizhou Wang , Yibo Yan , Yuanhuiyi Lyu , Kening Zheng , Sirui Huang , Junkai Chen , Peijie Jiang , Jia Liu , Chang Tang , Xuming Hu

Despite Video Large Language Models having rapidly advanced in recent years, perceptual hallucinations pose a substantial safety risk, which severely restricts their real-world applicability. While several methods for hallucination…

计算机视觉与模式识别 · 计算机科学 2025-12-23 Yiming Sun , Mi Zhang , Feifei Li , Geng Hong , Min Yang

Concerns regarding the propensity of Large Language Models (LLMs) to produce inaccurate outputs, also known as hallucinations, have escalated. Detecting them is vital for ensuring the reliability of applications relying on LLM-generated…

计算与语言 · 计算机科学 2024-05-31 Ernesto Quevedo , Jorge Yero , Rachel Koerner , Pablo Rivas , Tomas Cerny

Can Multimodal Large Language Models (MLLMs) develop an intuitive number sense similar to humans? Targeting this problem, we introduce Visual Number Benchmark (VisNumBench) to evaluate the number sense abilities of MLLMs across a wide range…

计算机视觉与模式识别 · 计算机科学 2025-08-01 Tengjin Weng , Jingyi Wang , Wenhao Jiang , Zhong Ming

Video Large Language Models (VideoLLMs) exhibit various types of hallucinations. Existing research has primarily focused on hallucinations involving the presence of events, objects, and scenes in videos, while largely neglecting event…

计算机视觉与模式识别 · 计算机科学 2026-01-16 Zefan Zhang , Kehua Zhu , Shijie Jiang , Hongyuan Lu , Shengkai Sun , Tian Bai

Large vision-language models (LVLMs) have demonstrated impressive capabilities across diverse multimodal tasks, yet they remain highly susceptible to visual hallucinations (VH), often producing confident but inaccurate descriptions of…

计算机视觉与模式识别 · 计算机科学 2025-08-19 Lexiang Tang , Xianwei Zhuang , Bang Yang , Zhiyuan Hu , Hongxiang Li , Lu Ma , Jinghan Ru , Yuexian Zou

We propose a novel text-to-video (T2V) generation benchmark, ChronoMagic-Bench, to evaluate the temporal and metamorphic capabilities of the T2V models (e.g. Sora and Lumiere) in time-lapse video generation. In contrast to existing…

计算机视觉与模式识别 · 计算机科学 2024-10-03 Shenghai Yuan , Jinfa Huang , Yongqi Xu , Yaoyang Liu , Shaofeng Zhang , Yujun Shi , Ruijie Zhu , Xinhua Cheng , Jiebo Luo , Li Yuan

Hallucination, a phenomenon where multimodal large language models~(MLLMs) tend to generate textual responses that are plausible but unaligned with the image, has become one major hurdle in various MLLM-related applications. Several…

计算机视觉与模式识别 · 计算机科学 2024-10-16 Han Qiu , Jiaxing Huang , Peng Gao , Qin Qi , Xiaoqin Zhang , Ling Shao , Shijian Lu

Text-to-image (T2I) models are capable of generating visually impressive images, yet they often fail to accurately capture specific attributes in user prompts, such as the correct number of objects with the specified colors. The diversity…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Kevin David Hayes , Micah Goldblum , Vikash Sehwag , Gowthami Somepalli , Ashwinee Panda , Tom Goldstein

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced the comprehension of multimedia content, bringing together diverse modalities such as text, images, and videos. However, a critical challenge faced…

计算机视觉与模式识别 · 计算机科学 2024-01-19 Li Sun , Liuan Wang , Jun Sun , Takayuki Okatani

Recently, Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in multi-modal context comprehension. However, they still suffer from hallucination problems referring to generating inconsistent outputs with the…

计算机视觉与模式识别 · 计算机科学 2024-09-02 Xiaoye Qu , Jiashuo Sun , Wei Wei , Yu Cheng

With the rapid development of multimodal models, the demand for assessing video understanding capabilities has been steadily increasing. However, existing benchmarks for evaluating video understanding exhibit significant limitations in…

计算机视觉与模式识别 · 计算机科学 2025-05-28 Qi Wu , Quanlong Zheng , Yanhao Zhang , Junlin Xie , Jinguo Luo , Kuo Wang , Peng Liu , Qingsong Xie , Ru Zhen , Zhenyu Yang , Haonan Lu

Video-language models (VLMs) achieve strong multimodal understanding but remain prone to hallucinations, especially when reasoning about actions and temporal order. Existing mitigation strategies, such as textual filtering or random video…

计算机视觉与模式识别 · 计算机科学 2026-01-09 Tobia Poppi , Burak Uzkent , Amanmeet Garg , Lucas Porto , Garin Kessler , Yezhou Yang , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara , Florian Schiffers

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

The reliability of large language models (LLMs) in production environments remains significantly constrained by their propensity to generate hallucinations -- fluent, plausible-sounding outputs that contradict or fabricate information.…