paper-with-me

Papers

A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models

2025-05-04 · Liqiang Jing, Guiming Hardy Chen, Ehsan Aghazadeh, Xin Eric Wang, Xinya Du

Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities in multimodal tasks, but visual object hallucination remains a persistent issue. It refers to scenarios where models generate inaccurate visual object-related information based on the query input, potentially leading to misinformation and concerns about safety and reliability. Previous works focus on the evaluation and mitigation of visual hallucinations, but the underlying causes have not been comprehensively investigated. In this paper, we analyze each component of LLaVA-like LVLMs -- the large language model, the vision backbone, and the projector -- to identify potential sources of error and their impact. Based on our observations, we propose methods to mitigate hallucination for each problematic component. Additionally, we developed two hallucination benchmarks: QA-VisualGenome, which emphasizes attribute and relation hallucinations, and QA-FB15k, which focuses on cognition-based hallucinations.

📄 PDF Abstract BibTeX arXiv:2505.01958

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeHallucinationLanguage ModelingLanguage ModellingLarge Language ModelMisinformationObject Hallucination

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Multi-Object Hallucination in Vision-Language Models

2024-07-08 · Xuweiyi Chen, Ziqiao Ma, Xuejun Zhang, Sihan Xu 외

Large vision language models (LVLMs) often suffer from object hallucination, producing objects not present in the given images. While current benchmarks for object hallucination primarily concentrate on the presence of a…

HallucinationObject Hallucination

Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models

2024-08-18 · Kening Zheng, Junkai Chen, Yibo Yan, Xin Zou 외

Hallucination issues continue to affect multimodal large language models (MLLMs), with existing research mainly addressing object-level or attribute-level hallucinations, neglecting the more complex relation hallucinatio…

AttributeHallucinationHallucination EvaluationRelation

Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models

2025-09-17 · Weihang Wang, Xinhao Li, Ziyue Wang, Yan Pang 외 arxiv

Object hallucination in Large Vision-Language Models (LVLMs) significantly impedes their real-world applicability. As the primary component for accurately interpreting visual information, the choice of visual encoder is …

VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models

2024-06-24 · Yuxuan Wang, Yueqian Wang, Dongyan Zhao, Cihang Xie 외

Recent advancements in Multimodal Large Language Models (MLLMs) have extended their capabilities to video understanding. Yet, these models are often plagued by "hallucinations", where irrelevant or nonsensical content is…

HallucinationVideo Understanding

On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models

2025-10-10 · Hoigi Seo, Dong Un Kang, Hyunjin Cho, Joohoon Lee 외 arxiv

Large vision-language models (LVLMs), which integrate a vision encoder (VE) with a large language model, have achieved remarkable success across various tasks. However, there are still crucial challenges in LVLMs such as…