EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Understanding Hallucinations in Large Visual and Language Models

Zheng Yi Ho, Siyuan Liang, Dacheng Tao

ACM Computing Surveys · 31.10.2026 · 58 (13) · 1-36

DOI: 10.1145/3811409 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 24.06.2026. Verfasst von Zheng Yi Ho und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 283 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Research Foundation, Singapore, and Cyber Security Agency of Singapore under its National Cybersecurity R&D Programme and CyberSG R&D Cyber Research P….

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid deployment of large language and vision models in real-world applications has intensified the need to address hallucinations—instances where models generate incorrect or incoherent outputs. These failures can spread misinformation and degrade workflows, causing financial and operational harm. Despite extensive research efforts, our understanding of hallucinations remains limited and fragmented. Without clear understanding, solutions risk addressing disparate symptoms rather than root causes, which undermines their effectiveness and generalisability during deployment. To address this, we first introduce a unified, multi-level framework to characterise both image and text hallucinations across broad applications, helping reduce conceptual fragmentation. Then, we trace their root causes to identifiable mechanisms within a model’s lifecycle in a task-modality interleaved manner, fostering a deeper and more holistic understanding. Our investigations reveal hallucinations as predictable consequences of underlying distributions and biases. By enhancing our understanding of hallucinations, this survey lays the groundwork for more effective solutions to hallucinations in generative AI systems.

Förderung

  • National Research Foundation, Singapore, and Cyber Security Agency of Singapore under its National Cybersecurity R&D Programme and CyberSG R&D Cyber Research P…

Zitieren

APA

Ho, Z. Y., Liang, S., & Tao, D. (2026). Understanding Hallucinations in Large Visual and Language Models. ACM Computing Surveys, 58(13), 1-36. https://doi.org/10.1145/3811409

Vancouver

Ho ZY, Liang S, Tao D. Understanding Hallucinations in Large Visual and Language Models. ACM Computing Surveys. 2026;58(13):1-36. doi:10.1145/3811409

BibTeX
@article{Ho2026,
  author = {Ho, Zheng Yi and Liang, Siyuan and Tao, Dacheng},
  title = {Understanding Hallucinations in Large Visual and Language Models},
  journal = {ACM Computing Surveys},
  year = {2026},
  volume = {58},
  number = {13},
  pages = {1--36},
  doi = {10.1145/3811409}
}
Kostenlos starten →