AI Hallucinations in Large Language Model and Multimodal Models: A Systematic Review of Causes, Types, Detection, Mitigation, and Future Directions
International Journal of Computer Sciences and Engineering · 30.06.2026 · 14 (6) · 26-33
DOI: 10.26438/ijcse.v14i6.7456 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift International Journal of Computer Sciences and Engineering, online erschienen am 30.06.2026. Verfasst von Mahender Singh und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Large language Models are really good at generating text that sounds natural. They often make things up. They create content that sounds convincing. It is not always true. This is a problem when these models are used in areas like healthcare, law and education. The main reason we cannot trust these models is that they make things up. There are studies about this issue but they are all, over the place. They look at reasons why language models make things up the different types of made-up information how to detect it and how to stop it. Most of these studies do not clearly explain how they were done or exactly how the models work. Language models are the problem and language models need to be fixed. This paper explores a problem that earlier research had left unexplored. It does this by reviewing existing studies and combining a mathematical theory with a clear step-, by-step approach. The researchers followed a process to find studies published between 2018 and 2026. They applied rules to screen these studies and narrowed them down to a smaller group. This group was then examined across eight themes. What they found is that AI “hallucinations” (when AI makes up false information) come from several factors working together: the data, the system's design, how it's trained, how it generates answers, and how it's tested. Recent theory suggests hallucination is a built-in feature of how these AI systems generate text, not a flaw that can simply be removed. They identified eight types of hallucinations, and these types vary in how hard they are to detect and correct. Some detection methods have improved, but the techniques used to reduce hallucinations only lessen the problem—they don't get rid of it completely. The most serious real-world harms show up in legal and medical settings.
Zitieren
APA
Singh, M., & Banerjee, S. (2026). AI Hallucinations in Large Language Model and Multimodal Models: A Systematic Review of Causes, Types, Detection, Mitigation, and Future Directions. International Journal of Computer Sciences and Engineering, 14(6), 26-33. https://doi.org/10.26438/ijcse.v14i6.7456
Vancouver
Singh M, Banerjee S. AI Hallucinations in Large Language Model and Multimodal Models: A Systematic Review of Causes, Types, Detection, Mitigation, and Future Directions. International Journal of Computer Sciences and Engineering. 2026;14(6):26-33. doi:10.26438/ijcse.v14i6.7456
BibTeX
@article{Singh2026,
author = {Singh, Mahender and Banerjee, Shyamol},
title = {AI Hallucinations in Large Language Model and Multimodal Models: A Systematic Review of Causes, Types, Detection, Mitigation, and Future Directions},
journal = {International Journal of Computer Sciences and Engineering},
year = {2026},
volume = {14},
number = {6},
pages = {26--33},
doi = {10.26438/ijcse.v14i6.7456}
}
EUVIMED