Large Language Models for Multimodal Fact-Checking: Methodological Advances and Persistent Challenges
Mathematics · 18.11.2026 · 14 (22) · 4243
DOI: 10.3390/math14224243 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 18.11.2026. Verfasst von Tiantian Zhu und 7 weiteren Autor:innen. Die Arbeit nennt 482 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Scientific Foundation for Youth Scholars of Shenzhen University, Internal Fund of the National Engineering Laboratory for Big Data System Computing Technology.
Abstract (Originalsprache)
Fact-checking aims to assign truth values to claims within a specified context. Unimodal fact-checking methods, due to modality fragmentation and inadequate adaptiveness, struggle in complex scenarios where multimodal misinformation is interconnected. The rapid advancement of generative large language models (LLMs) has provided a novel technological paradigm for multimodal fact-checking. With their capabilities in deep semantic understanding and cross-modal alignment, LLMs can significantly enhance the accuracy, interpretability, and generalizability of misinformation detection. Synthesizing representative studies from 2018 to 2026 retrieved via a multi-dimensional keyword search, two-step screening, and citation chaining, we comprehensively survey the subtask arrangements, LLM-based methodologies, and relevant datasets for both unimodal and multimodal fact-checking tasks. Following the standard fact-checking pipeline, we comprehensively review existing methods across four key stages, namely Claim Detection and Extraction, Evidence Retrieval, Verdict Prediction, and Justification Production, providing a structured perspective for method comparison and evaluation. Our synthesis indicates that while multimodal large language models (MLLMs) enhance cross-modal understanding and verification flexibility, fine-grained visual–textual consistency and evidential sufficiency remain critical challenges. We provide a comprehensive survey of fact-checking research and offer insights into the development of next-generation fact-checking systems expected to be more robust, scalable, and adaptable across diverse information environments.
Förderung
- National Natural Science Foundation of China
- Scientific Foundation for Youth Scholars of Shenzhen University
- Internal Fund of the National Engineering Laboratory for Big Data System Computing Technology
- Shenzhen Medical Research Fund
- Guangdong Basic and Applied Basic Research Foundation
- Shenzhen Science and Technology Program
- Independent Scientific Research Program of the State Key Laboratory of Radio Frequency Heterogeneous Integration
- Intelligent Computing Center of Shenzhen University
Zitieren
APA
Zhu, T., Wang, Z., Jin, X., Chen, Q., Zhang, J., Liu, Y., Zhu, Z., & Li, J. (2026). Large Language Models for Multimodal Fact-Checking: Methodological Advances and Persistent Challenges. Mathematics, 14(22), 4243. https://doi.org/10.3390/math14224243
Vancouver
Zhu T, Wang Z, Jin X, Chen Q, Zhang J, Liu Y, et al. Large Language Models for Multimodal Fact-Checking: Methodological Advances and Persistent Challenges. Mathematics. 2026;14(22):4243. doi:10.3390/math14224243
BibTeX
@article{Zhu2026,
author = {Zhu, Tiantian and Wang, Zhicong and Jin, Xiongnan and Chen, Qingcai and Zhang, Jun and Liu, Yumeng and Zhu, Zexuan and Li, Jianqiang},
title = {Large Language Models for Multimodal Fact-Checking: Methodological Advances and Persistent Challenges},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {22},
pages = {4243},
doi = {10.3390/math14224243}
}
EUVIMED