Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding

Recent advancements in multimodal large language models (MLLMs) have significantly improved performance in visual question answering. However, they often suffer from hallucinations. In this work, hallucinations are categorized into two main types: initial hallucinations and snowball hallucinations....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) Jg. 2025; S. 26147 - 26159
Hauptverfasser:	Tang, Feilong, Liu, Chengzhi, Xu, Zhongxing, Hu, Ming, Huang, Zile, Xue, Haochen, Chen, Ziyang, Peng, Zelin, Yang, Zhiwei, Zhou, Sijin, Li, Wenxue, Li, Yulong, Song, Wenxuan, Su, Shiyan, Feng, Wei, Su, Jionglong, Lin, Minquan, Peng, Yifan, Cheng, Xuelian, Razzak, Imran, Ge, Zongyuan
Format:	Tagungsbericht Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.06.2025
Schlagworte:	Data mining Decoding Encoding FarSight demonstrates significant hallucination-mitigating performance across different MLLMs on both image and video benchmarks Heart Interference Large language models proving its effectiveness Question answering (information retrieval) Registers Video sequences Visualization With extensive experiments
ISSN:	1063-6919, 1063-6919
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!