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。

2025-09-25 至 2025-09-25 共收录 3 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. 安全训练 3 篇

2509.19688 2025-09-25 cs.RO cs.LG cs.SY eess.SY math.OC 79%

Formal Safety Verification and Refinement for Generative Motion Planners via Certified Local Stabilization

Devesh Nath, Haoran Yin, Glen Chou

机构 * Georgia Institute of Technology（佐治亚理工学院）

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

Comments 10 pages, 12 figures

2509.19839 2025-09-25 cs.AI 70%

LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation

Huizhen Shu, Xuying Li, Zhuo Li

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

Comments 9-page NeurIPS 2025 preprint including 3 figures and 1 table, with additional appendix material. Prepared using the NeurIPS 2025 preprint template and compiled with pdfLaTeX. All references are included via the provided .bbl file. Figures are in PDF format. No external supplementary files. All necessary style files and images are included

2505.12621 2025-09-25 cs.CL cs.IR 70%

SAFE: Improving LLM Systems using Sentence-Level In-generation Attribution

João Eduardo Batista, Emil Vatai, Mohamed Wahib

机构 * RIKEN-CCS Kobe, Japan（日本神户RIKEN-CCS）

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

Comments 30 pages (9 pages of content, 5 pages of references, 16 pages of supplementary material), 7 figures, 13 tables