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。

2025-10-27 至 2025-10-27 共收录 5 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. 偏好对齐 5 篇

2505.17859 2025-10-27 cs.LG cs.AI stat.ML 86%

Scalable Valuation of Human Feedback through Provably Robust Model Alignment

Masahiro Fujisawa, Masaki Adachi, Michael A. Osborne

机构 * The University of Osaka（大阪大学）； Lattice Lab, Toyota Motor Corporation（丰田公司Lattice实验室）； Machine Learning Research Group, University of Oxford（牛津大学机器学习研究组）； RIKEN AIP（理化学研究所AIP）

专题命中偏好对齐：alignment(title,abstract)；RLHF(abstract)；DPO(abstract)；分类 cs.AI、cs.LG

Comments Accepted by the 39th Conference on Neural Information Processing Systems (NeurIPS2025), 49 pages, 7 figures

2509.21798 2025-10-27 cs.CL cs.AI 81%

Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment

Hongbin Zhang, Kehai Chen, Xuefeng Bai, Yang Xiang, Min Zhang

机构 * Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China（计算与智能研究所，哈尔滨工业大学，深圳，中国）； Peng Cheng Laboratory, Shenzhen, China（鹏城实验室，深圳，中国）

专题命中偏好对齐：alignment(title,abstract)；分类 cs.CL、cs.AI

Comments Under review;Work in progress;

2410.12854 2025-10-27 cs.CL cs.AI 73%

TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees

Weibin Liao, Xu Chu, Yasha Wang

机构 * School of Computer Science, Peking University（北京大学计算机科学系）； Center on Frontiers of Computing Studies, Peking University（北京大学前沿计算研究中心）； National Research and Engineering Center of Software Engineering, Peking University（北京大学软件工程研究中心）

专题命中偏好对齐：alignment(abstract)；DPO(abstract)；分类 cs.CL、cs.AI

Comments Accepted by ICLR 2025

2505.11475 2025-10-27 cs.CL cs.AI cs.LG 67%

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

Zhilin Wang, Jiaqi Zeng, Olivier Delalleau, Hoo-Chang Shin, Felipe Soares, Alexander Bukharin, Ellie Evans, Yi Dong, Oleksii Kuchaiev

机构 * NVIDIA

专题命中偏好对齐：RLHF(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NeurIPS 2025 Datasets and Benchmarks Track Camera Ready, 46 pages, 2 figures

2505.11080 2025-10-27 cs.CL cs.AI cs.LG 67%

BLEUBERI: BLEU is a surprisingly effective reward for instruction following

Yapei Chang, Yekyung Kim, Michael Krumdick, Amir Zadeh, Chuan Li, Chris Tanner, Mohit Iyyer

机构 * University of Maryland, College Park（马里兰大学学院公园分校）

专题命中偏好对齐：alignment(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments neurips cam-ready