Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{189969,
        author = {Vaibhav Kumar Tiwari and Partheeban Nagappan and Chandra Shekhar Tyagi and Harish Kumar},
        title = {A Systematic Survey of explainable Artificial Intelligence (XAI): Approaches, Uses and Open Problems},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {8},
        pages = {59-64},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189969},
        abstract = {Artificial Intelligence (AI) has already generated an astonishing advancement in various fields, but the sophistication and obscurity of the modern models restrict their trustworthiness to high-stakes settings. To address this gap, explainable Artificial Intelligence (XAI) has come into being to improve machine learning system transparency, interpretability, and accountability. This survey offers a summary of the state of XAI in 2020-2025 of model-agnostic methods including LIME and SHAP, and model-specific methods including GradCAM and Integrated Gradients. In the healthcare, financial, and autonomous systems, key applications are evaluated, and issues in assessment metrics, trade-offs between interpretability and accuracy, and ethical limitations are examined. In addition, new directions of human-centred and hybrid explainability are mentioned as prospective research planning. The conclusion of the study is that XAI is imperative in the creation of trustworthy, transparent, and socially responsible AI systems that can generate user confidence and regulatory adherence in the implementation phase of AI systems into practice.},
        keywords = {Explainable Artificial Intelligence (XAI), Interpretability, Transparency, Trustworthy AI, Machine Learning, Deep Learning, Human-centred AI, Ethical AI.},
        month = {December},
        }