大模型对齐与安全

Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection

Atoosa Chegini, Hamid Kazemi, Garrett Souza, Maria Safi, Yang Song, Samy Bengio, Sinead Williamson, Mehrdad Farajtabar

机构 * Apple（苹果公司） 纠错

专题命中 幻觉与事实性 ：safety(title,abstract)；分类 cs.CL、cs.AI、cs.LG

VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set

Shufan Shen, Junshu Sun, Qingming Huang, Shuhui Wang

机构 * Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS（智能信息处理重点实验室，计算技术研究所，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

专题命中 幻觉与事实性 ：alignment(title,abstract)；分类 cs.LG

Comments Accepted by NeurIPS 2025

Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty

Meera Hahn, Wenjun Zeng, Nithish Kannen, Rich Galt, Kartikeya Badola, Been Kim, Zi Wang

机构 * Google DeepMind（谷歌DeepMind） 纠错

专题命中 幻觉与事实性 ：alignment(abstract)；分类 cs.AI、cs.LG

Journal ref International Conference on Machine Learning, 2025