KAIST’s Center for Explainable AI has released an open-source plug-and-play framework that simplifies AI explainability without requiring expert knowledge. The framework automatically detects model structures, recommends compatible explanation algorithms, and provides visual and quantitative evaluations in its “Auto Explanation” mode. It supports various data types and has been successfully applied to medical and AI reliability use cases in collaboration with other institutions. This tool aims to overcome existing XAI limitations and enhance AI trustworthiness across domains. Available on GitHub under the Apache 2.0 license, it reflects years of collaboration by Korea’s top researchers.

AI times : https://www.aitimes.com/news/articleView.html?idxno=166532
KAIST News : https://news.kaist.ac.kr/news/html/news/?mode=V&mng_no=42851
Github Repo : https://github.com/OpenXAIProject/pnpxai