Black Box
"Black box" refers to systems whose internal workings are opaque, hindering understanding and analysis. Current research focuses on methods to analyze and mitigate the limitations of black-box models, particularly deep neural networks, across diverse applications like code generation, robot design, and autonomous systems. Key approaches involve developing surrogate models, employing novel optimization techniques, and designing explainable AI (XAI) methods to enhance interpretability and trustworthiness. This research is crucial for ensuring the safety, reliability, and fairness of increasingly prevalent AI systems in various fields.
Papers
Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanations
Koorosh Aslansefat, Mojgan Hashemian, Martin Walker, Mohammed Naveed Akram, Ioannis Sorokos, Yiannis Papadopoulos
ExpNote: Black-box Large Language Models are Better Task Solvers with Experience Notebook
Wangtao Sun, Xuanqing Yu, Shizhu He, Jun Zhao, Kang Liu
On the Interpretability of Part-Prototype Based Classifiers: A Human Centric Analysis
Omid Davoodi, Shayan Mohammadizadehsamakosh, Majid Komeili
A Black-Box Physics-Informed Estimator based on Gaussian Process Regression for Robot Inverse Dynamics Identification
Giulio Giacomuzzos, Ruggero Carli, Diego Romeres, Alberto Dalla Libera
Retromorphic Testing: A New Approach to the Test Oracle Problem
Boxi Yu, Qiuyang Mang, Qingshuo Guo, Pinjia He