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....

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) Ročník 2025; s. 26147 - 26159
Hlavní autoři:	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
Médium:	Konferenční příspěvek Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.06.2025
Témata:	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
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	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. We argue that adequate contextual information can be extracted directly from the token interaction process. Inspired by causal inference in the decoding strategy, we propose to leverage causal masks to establish information propagation between multimodal tokens. The hypothesis is that insufficient interaction between those tokens may lead the model to rely on outlier tokens, overlooking dense and rich contextual cues. Therefore, we propose to intervene in the propagation process by tackling outlier tokens to enhance in-context inference. With this goal, we present FarSight, a versatile plug-and-play decoding strategy to reduce attention interference from outlier tokens merely by optimizing the causal mask. The heart of our method is effective token propagation. We design an attention register structure within the upper triangular matrix of the causal mask, dynamically allocating attention to capture attention diverted to outlier tokens. Moreover, a positional awareness encoding method with a diminishing masking rate is proposed, allowing the model to attend to further preceding tokens, especially for video sequence tasks.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	1063-6919 1063-6919
DOI:	10.1109/CVPR52734.2025.02435