Review of Hallucination Understanding in Large Language and Vision Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ho, Zhengyi, Liang, Siyuan, Tao, Dacheng
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914069125005312
author Ho, Zhengyi
Liang, Siyuan
Tao, Dacheng
author_facet Ho, Zhengyi
Liang, Siyuan
Tao, Dacheng
contents The widespread adoption of large language and vision models in real-world applications has made urgent the need to address hallucinations -- instances where models produce incorrect or nonsensical outputs. These errors can propagate misinformation during deployment, leading to both financial and operational harm. Although much research has been devoted to mitigating hallucinations, our understanding of it is still incomplete and fragmented. Without a coherent understanding of hallucinations, proposed solutions risk mitigating surface symptoms rather than underlying causes, limiting their effectiveness and generalizability in deployment. To tackle this gap, we first present a unified, multi-level framework for characterizing both image and text hallucinations across diverse applications, aiming to reduce conceptual fragmentation. We then link these hallucinations to specific mechanisms within a model's lifecycle, using a task-modality interleaved approach to promote a more integrated understanding. Our investigations reveal that hallucinations often stem from predictable patterns in data distributions and inherited biases. By deepening our understanding, this survey provides a foundation for developing more robust and effective solutions to hallucinations in real-world generative AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00034
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Review of Hallucination Understanding in Large Language and Vision Models
Ho, Zhengyi
Liang, Siyuan
Tao, Dacheng
Computer Vision and Pattern Recognition
Artificial Intelligence
The widespread adoption of large language and vision models in real-world applications has made urgent the need to address hallucinations -- instances where models produce incorrect or nonsensical outputs. These errors can propagate misinformation during deployment, leading to both financial and operational harm. Although much research has been devoted to mitigating hallucinations, our understanding of it is still incomplete and fragmented. Without a coherent understanding of hallucinations, proposed solutions risk mitigating surface symptoms rather than underlying causes, limiting their effectiveness and generalizability in deployment. To tackle this gap, we first present a unified, multi-level framework for characterizing both image and text hallucinations across diverse applications, aiming to reduce conceptual fragmentation. We then link these hallucinations to specific mechanisms within a model's lifecycle, using a task-modality interleaved approach to promote a more integrated understanding. Our investigations reveal that hallucinations often stem from predictable patterns in data distributions and inherited biases. By deepening our understanding, this survey provides a foundation for developing more robust and effective solutions to hallucinations in real-world generative AI systems.
title Review of Hallucination Understanding in Large Language and Vision Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.00034