Copyright © 2026 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{191723,
        author = {Kajal Sinha},
        title = {Enhancing Transparency and Trust in Artificial Intelligence Systems Using Explainable AI (XAI) Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {12},
        number = {no},
        pages = {64-67},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191723},
        abstract = {AI models - particularly deep learning ones - are super complicated, so we can’t always see how they make decisions. Even though this complexity boosts their performance, it makes things unclear, making people doubt them. Since AI is now used more in areas like healthcare or justice, understanding its choices matters a lot - for ethics, rules, and safety. XAI helps break down what’s happening inside these systems using explanations regular folks can grasp, which builds trust, reduces bias, while holding systems answerable. This work looks at why being able to understand AI decisions matters. It checks out key methods that explain models no matter their type, along with ones built for specific systems. A mix of LIME and SHAP is suggested - bringing together two styles of explanation tools. This combo tries to make sense of predictions both near (for single cases) and far (overall patterns), giving clearer, steadier insights people can actually use. Tests show it works well without slowing down or weakening the main model’s accuracy. In the end, the research pushes for flexible, adaptable explanation tools tuned to different fields, especially as AI moves into areas where mistakes could be serious.},
        keywords = {Explainable Artificial Intelligence (XAI), Model Interpretability, Deep Learning Transparency, Trustworthy AI, Ethical AI, AI Accountability},
        month = {},
        }