大模型对齐与安全

AttAnchor: Guiding Cross-Modal Token Alignment in VLMs with Attention Anchors

Junyang Zhang, Tianyi Zhu, Thierry Tambe

机构 * California Institute of Technology（加州理工学院） ； Stanford University（斯坦福大学） 纠错

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

Comments 31 pages, 17 figures

Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty

Lingyou Pang, Lei Huang, Jianyu Lin, Tianyu Wang, Akira Horiguchi, Alexander Aue, Carey E. Priebe

机构 * Department of Statistics, University of California, Davis（加州大学戴维斯分校统计系） ； Department of Applied Mathematics and Statistics, Johns Hopkins University（约翰霍普金斯大学应用数学与统计学系） 纠错

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

Comments 26 pages including appendix; 3 figures and 5 tables. Under review for ICLR 2026

Calibration Meets Reality: Making Machine Learning Predictions Trustworthy

Kristina P. Sinaga, Arjun S. Nair

机构 * Independent Researcher（独立研究者） 纠错

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

Comments 30 pages, 7 figures, 5 tables

How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation

Ruohao Guo, Wei Xu, Alan Ritter

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

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

Comments Accepted to EMNLP 2025 main conference

Dynamic Trust Calibration Using Contextual Bandits

Bruno M. Henrique, Eugene Santos

机构 * Thayer School of Engineering（泰勒工程学院） ； Dartmouth College（达特茅斯学院） 纠错

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

Tree Reward-Aligned Search for TReASURe in Masked Diffusion Language Models

Zichao Yu, Ming Li, Wenyi Zhang, Weiguo Gao

机构 * University of Science and Technology of China（中国科学技术大学） ； Fudan University（复旦大学） 纠错

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

Comments 21 pages, 6 figures

The Geometry of Creative Variability: How Credal Sets Expose Calibration Gaps in Language Models

Esteban Garces Arias, Julian Rodemann, Christian Heumann

机构 * Department of Statistics, LMU Munich（统计系，慕尼黑大学） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） ； CISPA Helmholtz Center for Information Security（信息安全赫尔姆霍兹研究中心） 纠错

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

Comments Accepted at the 2nd UncertaiNLP Workshop @ EMNLP 2025

KAQG: A Knowledge-Graph-Enhanced RAG for Difficulty-Controlled Question Generation

Ching Han Chen, Ming Fang Shiu

专题命中 幻觉与事实性 ：alignment(abstract)

Comments 10 pages, 4 figures and 6 tables

No Concept Left Behind: Test-Time Optimization for Compositional Text-to-Image Generation

Mohammad Hossein Sameti, Amir M. Mansourian, Arash Marioriyad, Soheil Fadaee Oshyani, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah

机构 * Sharif University of Technology（沙里夫技术大学） 纠错

专题命中 幻觉与事实性 ：alignment(abstract)

Comments 8 pages, 8 figures, 1 table

Situational Awareness for Safe and Robust Multi-Agent Interactions Under Uncertainty

Benjamin Alcorn, Eman Hammad

专题命中 幻觉与事实性 ：safety(abstract)