COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees

Zhiyuan Wang, Jinhao Duan, Qingni Wang, Xiaofeng Zhu 0001, Tianlong Chen 0001, Xiaoshuang Shi, Kaidi Xu. COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees. In Sven Koenig, Chad Jenkins, Matthew E. Taylor, editors, Fortieth AAAI Conference on Artificial Intelligence, Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence, Sixteenth Symposium on Educational Advances in Artificial Intelligence, AAAI 2026, Singapore, January 20-27, 2026. pages 33764-33772, AAAI Press, 2026. [doi]

Abstract

Abstract is missing.