paper-with-me

홈 › Papers

Magnifier Prompt: Tackling Multimodal Hallucination via Extremely Simple Instructions

2024-10-15 · Yuhan Fu, Ruobing Xie, Jiazhen Liu, Bangxiang Lan, Xingwu Sun, Zhanhui Kang, Xirong Li

Hallucinations in multimodal large language models (MLLMs) hinder their practical applications. To address this, we propose a Magnifier Prompt (MagPrompt), a simple yet effective method to tackle hallucinations in MLLMs via extremely simple instructions. MagPrompt is based on the following two key principles, which guide the design of various effective prompts, demonstrating robustness: (1) MLLMs should focus more on the image. (2) When there are conflicts between the image and the model's inner knowledge, MLLMs should prioritize the image. MagPrompt is training-free and can be applied to open-source and closed-source models, such as GPT-4o and Gemini-pro. It performs well across many datasets and its effectiveness is comparable or even better than more complex methods like VCD. Furthermore, our prompt design principles and experimental analyses provide valuable insights into multimodal hallucination.

📄 PDF Abstract BibTeX arXiv:2410.11701

Code (0)

등록된 구현이 없습니다.

Tasks

Hallucination

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Magnifier: A Multi-grained Neural Network-based Architecture for Burned Area Delineation

2025-04-28 · Daniele Rege Cambrin, Luca Colomba, Paolo Garza

In crisis management and remote sensing, image segmentation plays a crucial role, enabling tasks like disaster response and emergency planning by analyzing visual data. Neural networks are able to analyze satellite acqui…

Burned Area DelineationDisaster ResponseImage SegmentationSemantic Segmentation

MedPromptX: Grounded Multimodal Prompting for Chest X-ray Diagnosis

2024-03-22 · Mai A. Shaaban, Adnan Khan, Mohammad Yaqub

Chest X-ray images are commonly used for predicting acute and chronic cardiopulmonary conditions, but efforts to integrate them with structured clinical data face challenges due to incomplete electronic health records (E…

Medical DiagnosisMedical Visual Question AnsweringVisual GroundingVisual Question Answering+2

OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination

2025-08-31 · Junzhe Chen, Tianshu Zhang, Shiyu Huang, Yuwei Niu 외 arxiv

Recently, Omni-modal large language models (OLLMs) have sparked a new wave of research, achieving impressive results in tasks such as audio-video understanding and real-time environment perception. However, hallucination…

Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decoding

2025-03-13 · Shunqi Mao, Chaoyi Zhang, Weidong Cai

Existing vision-language models (VLMs) often suffer from visual hallucination, where the generated responses contain inaccuracies that are not grounded in the visual input. Efforts to address this issue without model fin…

HallucinationText Generation

VIGIL: Tackling Hallucination Detection in Image Recontextualization

2026-02-16 · Joanna Wojciechowicz, Maria Łubniewska, Jakub Antczak, Justyna Baczyńska 외 arxiv

We introduce VIGIL (Visual Inconsistency & Generative In-context Lucidity), the first benchmark dataset and framework providing a fine-grained categorization of hallucinations in the multimodal image recontextualization …