大模型对齐与安全

SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment

Wonje Jeung, Sangyeon Yoon, Minsuk Kahng, Albert No

机构 * Department of Artificial Intelligence, Yonsei University（人工智能系，延世大学） ； Department of Computer Science and Engineering, Yonsei University（计算机科学与工程系，延世大学） 纠错

专题命中 安全训练 ：alignment(title,abstract)；safety(abstract)；jailbreak(abstract)；分类 cs.CL、cs.AI

Comments Accepted at NeurIPS 2025. Code and models are available at https://ai-isl.github.io/safepath

Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values

Dian Yu, Yulai Zhao, Kishan Panaganti, Linfeng Song, Haitao Mi, Dong Yu

专题命中 安全训练 ：alignment(abstract)；分类 cs.CL、cs.LG

Comments 15 pages, 4 figures

MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance

Agam Goyal, Xianyang Zhan, Yilun Chen, Koustuv Saha, Eshwar Chandrasekharan

机构 * Siebel School of Computing and Data Science（计算机与数据科学学院） 纠错

专题命中 安全训练 ：trustworthy(abstract)；分类 cs.CL

Comments EMNLP 2025 (Oral)