Nirmalendu Prakash, Wei Jie Yeo, Amir Abdullah, Ranjan Satapathy, Erik Cambria, Roy Ka-Wei Lee. Beyond I'm Sorry, I Can't: Dissecting Large-Language-Model Refusal. 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 37830-37838, AAAI Press, 2026. [doi]
Abstract is missing.