• Dr Monika Rathore

Abstract: In recent years Artificial Intelligence and Machine Learning have shown an outstanding performance and have achieved notable attention both in the field of Research and various Industries. And Deep Learning has made a significant contribution in the field of AI. However Deep Learning is treated as a black box because it is unable to give the explanation about how a system has planned or has achieved a particular result. And if a human needs to accept a particular system one needs to understand why/why not the system works. And human users must be able to determine when to trust the system and when the system should not be trusted. In the real-world applications explainability has become essential for both the people and developers who are affected by AI decisions. The decision made by the system can sometime be critical to life, death, and personal wellness. So, there is a need for proper explanation about the decision made by the system. There is a need to approximate the black box in an interpretable way. Explainable Artificial Intelligence (XAI) is a method used in AI which tells how a particular system decides which can be understood by humans or gives an explanation how a system arrives at a particular solution. When a user gets an explanation, he knows when to trust and distrust a system. IndexTerms: Explainable AI(XAI), LRP, LIME

: Explainable AI(XAI), LRP, LIME

"Explainability Enhancement in Orange Tool: A Hybrid LIME–LRP Interpretation Framework for Neural Models", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 3, page no.g749-g754, March-2026, Available :http://www.jetir.org/papers/JETIR2603695.pdf

"Explainability Enhancement in Orange Tool: A Hybrid LIME–LRP Interpretation Framework for Neural Models", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 3, page no. ppg749-g754, March-2026, Available at : http://www.jetir.org/papers/JETIR2603695.pdf