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。

2025-10-21 至 2025-10-21 共收录 6 篇信号源：cs.CL, cs.AI, cs.CY, cs.LG

1. 幻觉与事实性 6 篇

2510.16257 2025-10-21 cs.CL 79%

Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedback

Chu Fei Luo, Samuel Dahan, Xiaodan Zhu

机构 * Department of Electrical and Computer Engineering & Ingenuity Labs Research Institute（电气与计算机工程系及创新实验室研究机构）； Conflict Analytics Lab, Queen’s University（冲突分析实验室，女王大学）； Cornell Law School（康奈尔法学院）

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

Comments Findings of EMNLP 2025, 5 pages

2502.17598 2025-10-21 cs.LG cs.AI cs.CL 67%

Hallucination Detection in LLMs Using Spectral Features of Attention Maps

Jakub Binkowski, Denis Janiak, Albert Sawczyn, Bogdan Gabrys, Tomasz Kajdanowicz

机构 * Wroclaw University of Science and Technology（沃拉日-克拉夫大学科学与技术学院）； University of Technology Sydney（悉尼技术大学）

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

Comments Accepted to EMNLP 2025. Code available at https://github.com/graphml-lab-pwr/lapeigvals

2504.14345 2025-10-21 q-fin.PM cs.AI 57%

LLM-Enhanced Black-Litterman Portfolio Optimization

Youngbin Lee, Yejin Kim, Juhyeong Kim, Suin Kim, Yongjae Lee

机构 * Elice AI Quant Lab, MODULABS Seoul Republic of Korea ； Meritz Fire \& Marine Insurance AI Quant Lab, MODULABS Seoul Republic of Korea ； Mirae Asset Global Investments AI Quant Lab, MODULABS Seoul Republic of Korea ； Ulsan National Institute of Science ； Elice AI Quant Lab, MODULABS ； Meritz Fire \& Marine Insurance AI Quant Lab, MODULABS ； Mirae Asset Global Investments AI Quant Lab, MODULABS

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

Comments Presented at the CIKM 2025 Workshop on Financial AI (https://advancesinfinancialai.com/)

2510.16376 2025-10-21 math.OC cs.AI cs.RO cs.SY eess.SY math.ST stat.TH 57%

Conformal Prediction in The Loop: A Feedback-Based Uncertainty Model for Trajectory Optimization

Han Wang, Chao Ning

机构 * School of Automation and Intelligent Sensing（自动化与智能感知学院）； Shanghai Jiao Tong University（上海交通大学）

专题命中幻觉与事实性：safety(abstract)；分类 cs.AI

Comments Accepted by NeurIPS 2025 Main Track

2510.16359 2025-10-21 cs.CL 57%

Utilising Large Language Models for Generating Effective Counter Arguments to Anti-Vaccine Tweets

Utsav Dhanuka, Soham Poddar, Saptarshi Ghosh

专题命中幻觉与事实性：alignment(abstract)；分类 cs.CL

Comments 14 pages, 1 figure, work done as a part of B.Tech project at IIT Kharagpur

2504.13169 2025-10-21 cs.CV 50%

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling

Tsung-Han Wu, Heekyung Lee, Jiaxin Ge, Joseph E. Gonzalez, Trevor Darrell, David M. Chan

机构 * UC Berkeley（加州大学伯克利分校）； POSTECH

专题命中幻觉与事实性：safety(abstract)

Comments Accepted to NeurIPS 2025; Project Page: https://reverse-vlm.github.io