2026· ITM Web of Conferences· 0 citations· 26 references
TL;DR
This work presents the basic principles, techniques, and evaluation frameworks for developing explainable multimodal AI systems that effectively balance accuracy and transparency with reliability and investigates the impact of explainability on reliability, fairness, and user trust in high-stakes sectors including healthcare, autonomous systems, and security applications.
Abstract
Multimodal AI (XMAI) systems incorporate various data modalities, including text, speech, images, sensor data, and structured data, to facilitate more informed human decision-making. Multimodal fusion significantly enhances predictive accuracy; however, it concurrently increases system complexity, thereby rendering interpretability a critical concern. This work presents the basic principles, techniques, and evaluation frameworks for developing explainable multimodal AI systems that effectively balance accuracy and transparency with reliability. We further investigate several fusion-aware explainability techniques: modality-specific saliency mapping, visualization of cross-modal attention, interpretable representation learning, and counterfactual reasoning across modalities. The study further investigates the impact of explainability on reliability, fairness, and user trust in high-stakes sectors including healthcare, autonomous systems, and security applications. An integrated XMAI framework is put forward, and open research challenges are discussed; explanation consistency, multimodal bias detection, and human-centered evaluation are some of the challenges in order to further encourage transparent, accountable, and trustworthy multimodal AI.
A unified learning paradigm is proposed that jointly optimizes predictive performance and modality-specific explainability by identifying the most informative elements inside each modality that contribute to diagnostic decisions by employing a matrix-based Renyi's $\alpha$-order entropy functional under the assumption...
Yu-Qing Yang, Alexander Schmatz, Zhao-Zhao Ma et al.· 0 citations
It is concluded that explainability is a necessary, though not sufficient, condition for trustworthy Al, and concrete directions for future research are outlined, including standardised benchmarks, human-centred evaluation, and explainability for large generative models.
Afna Ashraff M, Archana K, Buthaina Buthaina et al.· International Journal of Tec...· 0 citations
T-MoXAI (Temporal Multimodal eXplainable AI) provides a baseline for temporal multimodal XAI, addressing fragmentation in the field and supporting applications where understanding decisions is as important as predictive accuracy.
It is argued that meaningful clinical impact will require the integration of multimodal learning, semantic knowledge representation, explainable reasoning, and human-in-the-loop decision processes to support safe, interpretable, and clinically deployable AI systems in pediatric healthcare environments.
R. Zgheib, Alia El Naggar, Arash Kermani Kolankeh et al.· Information· 1 citation
. As artificial intelligence evolves, medical question-answering systems are changing to generative artificial intelligence (AIGC). Nevertheless, the general large-scale language models cannot find clinical applications yet because of the lack of multimodal perception, hallucinations, no clear reasoning chains, and the...
Hao-Cong Lin· Proceedings of the 4th Inter...· 0 citations
This survey presents an information-theoretic perspective connecting Mutual Information, the Information Bottleneck, and Partial Information Decomposition as progressively refined views of multimodal information processing, and discusses how emerging multimodal foundation models instantiate these principles at scale.
Liang-Jian Wen, Lin Li, Jiang Duan et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.