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。

2025-08-18 至 2025-08-18 共收录 3 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. 安全训练 3 篇

2411.02957 2025-08-18 cs.LG cs.SY eess.SY 79%

Embedding Safety into RL: A New Take on Trust Region Methods

Nikola Milosevic, Johannes Müller, Nico Scherf

机构 * Max Planck Institute for Human Cognitive and Brain Sciences（马克斯·普朗克人类认知与脑科学研究所）； Center for Scalable Data Analytics and Artificial Intelligence（可扩展数据分析与人工智能中心）

专题命中安全训练：safety(title,abstract)；分类 cs.LG

Comments Accepted at ICML 2025

Journal ref Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada. PMLR 267, 2025

2508.09666 2025-08-18 cs.CL 70%

Slow Tuning and Low-Entropy Masking for Safe Chain-of-Thought Distillation

Ziyang Ma, Qingyue Yuan, Linhai Zhang, Deyu Zhou

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

Comments Preprint

2508.11504 2025-08-18 cs.LG cs.CY 62%

Predicting and Explaining Traffic Crash Severity Through Crash Feature Selection

Andrea Castellani, Zacharias Papadovasilakis, Giorgos Papoutsoglou, Mary Cole, Brian Bautsch, Tobias Rodemann, Ioannis Tsamardinos, Angela Harden

机构 * Honda Research Institute Europe（霍恩达欧洲研究机构）； The Ohio State University（俄亥俄州立大学）； Department of Computer Science, University of Crete（克里特大学计算机科学系）； American Honda Motor Co., Inc.（美国本田摩托公司）

专题命中安全训练：safety(abstract)；分类 cs.CY、cs.LG

Comments Preprint. Manuscript under review at "Accident Analysis & Prevention" journal