AAAI

Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection

Chengcan Wu, Zeming Wei, Huanran Chen, Yinpeng Dong, Meng Sun

机构 * Peking University（北京大学） ； Tsinghua University（清华大学） 纠错

Comments 10 pages, 9 figures, Under review as a full paper at AAAI 2026. A preliminary version is under review at the NeurIPS 2025 Workshop on Reliable ML from Unreliable Data

A Moral Agency Framework for Legitimate Integration of AI in Bureaucracies

Chris Schmitz, Joanna Bryson

Comments Abstract to appear (non-archival) in Proceedings of the 8th AAAI/ACM Conference on AI, Ethics, and Society

A Case for Specialisation in Non-Human Entities

El-Mahdi El-Mhamdi, Lê-Nguyên Hoang, Mariame Tighanimine

Comments Accepted to AAAI/ACM AIES 2025