AI 大模型

大模型对齐与安全

大模型对齐、安全、越狱、红队、提示注入和可信评测。

2025-10-10 至 2025-10-10 共收录 2 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. AI治理与伦理 2 篇

2510.07613 2025-10-10 cs.CL cs.AI 62%

Vocabulary embeddings organize linguistic structure early in language model training

Isabel Papadimitriou, Jacob Prince

专题命中 AI治理与伦理：alignment(abstract)；分类 cs.CL、cs.AI

2510.08086 2025-10-10 cs.AI 57%

From Ethical Declarations to Provable Independence: An Ontology-Driven Optimal-Transport Framework for Certifiably Fair AI Systems

Sukriti Bhattacharya, Chitro Majumdar

机构 * Senior Scientist, Trustworthy AI, Luxembourg Institute of Science \& Technology, Maison de l'innovation 5, L-4362, Luxembourg Chief Investment Risk Strategist for Sovereign Institutions Founder, RsRL, Jumeirah Beach Residence (JBR), P.O.Box 29215, Dubai, United Arab Emirates

专题命中 AI治理与伦理：trustworthy(abstract)；分类 cs.AI

Comments 19 pages, 2 figures