article · Neural Processing Letters
Explainable artificial intelligence addresses the lack of transparency in complex models, which currently restricts their adoption in critical institutional decision-making. Recent developments focus on bridging the gap between intricate system behaviours and human comprehension to cultivate trust. Key methodological approaches under review include post-hoc explanation tools, inherent model transparency techniques, and interactive visualisation methods. Evaluating the specific strengths and weaknesses of these techniques demonstrates how advanced interpretability allows people to better scrutinise and comprehend machine learning outputs. Furthermore, examining local use cases illustrates how these methods function in practice while clarifying persisting implementation hurdles and future research priorities. Enhancing model interpretability supports the responsible and accountable deployment of automated tools across various operational settings, including healthcare and financial systems.
Complex artificial intelligence often operates as an opaque system, leaving users unsure of how conclusions are reached. By reviewing techniques that make automated decisions explainable and visually interactive, this work highlights pathways to establish accountability. Clearer explanations allow professionals to scrutinise algorithmic decisions responsibly before relying on them in high-stakes fields such as healthcare and finance.
The work addresses applications in high-stakes sectors such as healthcare and finance, where decision-makers require transparent algorithmic rationales. Potential users include institutions deploying machine learning within critical workflows. As an in-depth review examining existing methods, local use cases, and open research challenges, the study sits at an early, foundational stage of development rather than representing a standalone market-ready product.
AI-generated from the published abstract. Always read the original work before citing.
Recent advancements in Explainable Artificial Intelligence (XAI) aim to bridge the gap between complex artificial intelligence (AI) models and human understanding, fostering trust and usability in AI systems. However, challenges persist in comprehensively interpreting these models, hindering their widespread adoption. This study addresses these challenges by exploring recently emerging techniques in XAI. The primary problem addressed is the lack of transparency and interpretability in AI models to humanity for institution-wide use, which undermines user trust and inhibits their integration into critical decision-making processes. Through an in-depth review, this study identifies the objectives of enhancing the interpretability of AI models and improving human understanding of their decision-making processes. Various methodological approaches, including post-hoc explanations, model transparency methods, and interactive visualization techniques, are investigated to elucidate AI model behaviours. We further present techniques and methods to make AI models more interpretable and understandable to humans including their strengths and weaknesses to demonstrate promising advancements in model interpretability, facilitating better comprehension of complex AI systems by humans. In addition, we provide the application of XAI in local use cases. Challenges, solutions, and open research directions were highlighted to clarify these compelling XAI utilization challenges. The implications of this research are profound, as enhanced interpretability fosters trust in AI systems across diverse applications, from healthcare to finance. By empowering users to understand and scrutinize AI decisions, these techniques pave the way for more responsible and accountable AI deployment.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s11063-025-11732-2
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
