大模型对齐与安全 - arXivDaily 专题

2506.07882 2025-06-10 cs.CR 50%

Evaluating explainable AI for deep learning-based network intrusion detection system alert classification

Rajesh Kalakoti, Risto Vaarandi, Hayretdin Bahsi, Sven Nõmm

专题命中幻觉与事实性：alignment(abstract)

Comments Accepted version of a paper published in the Proceedings of the 11th International Conference on Information Systems Security and Privacy (ICISSP 2025). Final version available via SCITEPRESS

2504.19989 2025-06-09 cs.RO 50%

HJRNO: Hamilton-Jacobi Reachability with Neural Operators

Yankai Li, Mo Chen

机构 * School of Computing Science（计算科学学院）； Simon Fraser University（西蒙弗雷泽大学）

专题命中幻觉与事实性：safety(abstract)

2506.01595 2025-06-03 cs.SE 50%

A Systematic Mapping Study on Software Architecture for AI-based Mobility Systems

Amra Ramic, Stefan Kugele

专题命中幻觉与事实性：safety(abstract)

Comments 8 pages, 10 figures, 4 tables

2505.24282 2025-06-02 cs.CV 50%

LLM-powered Query Expansion for Enhancing Boundary Prediction in Language-driven Action Localization

Zirui Shang, Xinxiao Wu, Shuo Yang

机构 * Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology（北京智能信息科技重点实验室，计算机科学与技术学院）； Beijing Institute of Technology（北京理工大学）； Guangdong Laboratory of Machine Perception and Intelligent Computing（广东机器感知与智能计算实验室）； Shenzhen MSU-BIT University（深圳MSU-BIT大学）

专题命中幻觉与事实性：alignment(abstract)

2505.22551 2025-05-29 cs.CV stat.AP 50%

Deep Learning-Based BMD Estimation from Radiographs with Conformal Uncertainty Quantification

Long Hui, Wai Lok Yeung

机构 * Sky Long Artificial Intelligence Company（Sky Long人工智能公司）； Berkeley（伯克利）

专题命中幻觉与事实性：trustworthy(abstract)

2505.20236 2025-05-27 cs.CV 50%

Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models

Weihao Xuan, Qingcheng Zeng, Heli Qi, Junjue Wang, Naoto Yokoya

专题命中幻觉与事实性：alignment(abstract)

2504.16734 2025-05-20 cs.RO 50%

DYNUS: Uncertainty-aware Trajectory Planner in Dynamic Unknown Environments

Kota Kondo, Mason Peterson, Nicholas Rober, Juan Rached Viso, Lucas Jia, Jialin Chen, Harvey Merton, Jonathan P. How

专题命中幻觉与事实性：safety(abstract)

Comments 20 pages, 30 figures, Under review at IEEE Transactions on Robotics

2410.03577 2025-05-09 cs.CV 50%

Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models

Xin Zou, Yizhou Wang, Yibo Yan, Yuanhuiyi Lyu, Kening Zheng, Sirui Huang, Junkai Chen, Peijie Jiang, Jia Liu, Chang Tang, Xuming Hu

专题命中幻觉与事实性：alignment(abstract)

Comments Accepted by ICML 2025

2311.14284 2025-05-07 cs.CV 50%

Paragraph-to-Image Generation with Information-Enriched Diffusion Model

Weijia Wu, Zhuang Li, Yefei He, Mike Zheng Shou, Chunhua Shen, Lele Cheng, Yan Li, Tingting Gao, Di Zhang

机构 * Kuaishou Technology（快手科技）； Zhejiang University（浙江大学）； Show Lab, National University of Singapore（新加坡国立大学Show实验室）

专题命中幻觉与事实性：alignment(abstract)

Comments The project website is at: https://weijiawu.github.io/ParaDiffusionPage/. Code: https://github.com/weijiawu/ParaDiffusion

Journal ref IJCV 2025

2412.13695 2025-05-01 cs.CV 50%

Optical aberrations in autonomous driving: Physics-informed parameterized temperature scaling for neural network uncertainty calibration

Dominik Werner Wolf, Alexander Braun, Markus Ulrich

机构 * Machine Vision Metrology Group of the Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院机器视觉计量组）； Volkswagen Group（大众集团）； Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）； University of Applied Sciences Duesseldorf (HSD)（杜塞尔多夫应用技术大学）

专题命中幻觉与事实性：trustworthy(abstract)

Comments Under review at IEEE Transactions on Intelligent Transportation Systems (T-ITS)

2504.18525 2025-04-28 physics.ins-det cond-mat.mtrl-sci 50%

Automating Nanoindentation: Optimizing Workflows for Precision and Accuracy

Vivek Chawla, Dayakar Penumadu, Sergei Kalinin

专题命中幻觉与事实性：alignment(abstract)

Comments 26 pages (Including supplemental information), 13 figures, 0 Tables

2312.02252 2025-04-28 cs.CV 50%

StoryGPT-V: Large Language Models as Consistent Story Visualizers

Xiaoqian Shen, Mohamed Elhoseiny

机构 * KAUST（卡塞姆大学）

专题命中幻觉与事实性：alignment(abstract)

Comments Accepted to CVPR 2025; Project page: https://xiaoqian-shen.github.io/StoryGPT-V

2504.15263 2025-04-22 cs.RO 50%

Interpretable Locomotion Prediction in Construction Using a Memory-Driven LLM Agent With Chain-of-Thought Reasoning

Ehsan Ahmadi, Chao Wang

机构 * Bert S. Turner Department of Construction Management, Louisiana State University, Baton Rouge, LA 70803（伯特·S·特纳建设管理系，路易斯安那州立大学，巴吞鲁日，LA 70803）

专题命中幻觉与事实性：safety(abstract)

2504.11569 2025-04-17 eess.SY cs.SY 50%

Multi-Agent Reinforcement Learning for Decentralized Reservoir Management via Murmuration Intelligence

Heming Fu, Guojun Xiong, Jian Li, Shan Lin

专题命中幻觉与事实性：alignment(abstract)

Comments ACM SIGMETRICS 2025 Workshop

2408.11706 2025-04-08 cs.CV 50%

FRAP: Faithful and Realistic Text-to-Image Generation with Adaptive Prompt Weighting

Liyao Jiang, Negar Hassanpour, Mohammad Salameh, Mohan Sai Singamsetti, Fengyu Sun, Wei Lu, Di Niu

专题命中幻觉与事实性：alignment(abstract)

Comments TMLR 2025

2503.16707 2025-03-31 cs.CV 50%

Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding

Jinlong Li, Cristiano Saltori, Fabio Poiesi, Nicu Sebe

专题命中幻觉与事实性：alignment(abstract)

Comments Accepted by CVPR 2025

2503.14679 2025-03-20 physics.ins-det cond-mat.mtrl-sci stat.AP 50%

AI-driven Uncertainty Quantification & Multi-Physics Approach to Evaluate Cladding Materials in a Microreactor

Alex Foutch, Kazuma Kobayashi, Ayodeji Alajo, Dinesh Kumar, Syed Bahauddin Alam

专题命中幻觉与事实性：safety(abstract)

2405.10008 2025-03-19 cs.CV 50%

Solving the enigma: Enhancing faithfulness and comprehensibility in explanations of deep networks

Michail Mamalakis, Antonios Mamalakis, Ingrid Agartz, Lynn Egeland Mørch-Johnsen, Graham Murray, John Suckling, Pietro Lio

专题命中幻觉与事实性：trustworthy(abstract)

Comments Accepted manuscript in AI Open Journal (https://www.sciencedirect.com/journal/ai-open)

2503.04191 2025-03-13 cs.CV 50%

Conformal forecasting for surgical instrument trajectory

Sara Sangalli, Gary Sarwin, Ertunc Erdil, Alessandro Carretta, Victor Staartjes, Carlo Serra, Ender Konukoglu

专题命中幻觉与事实性：safety(abstract)

2408.11196 2025-03-05 cs.CV 50%

Robust Long-Range Perception Against Sensor Misalignment in Autonomous Vehicles

Zi-Xiang Xia, Sudeep Fadadu, Yi Shi, Louis Foucard

专题命中幻觉与事实性：safety(abstract)

2502.15722 2025-02-26 cs.IR cs.HC 50%

Open-Source Retrieval Augmented Generation Framework for Retrieving Accurate Medication Insights from Formularies for African Healthcare Workers

Axum AI, :, J. Owoyemi, S. Abubakar, A. Owoyemi, T. O. Togunwa, F. C. Madubuko, S. Oyatoye, Z. Oyetolu, K. Akyea, A. O. Mohammed, A. Adebakin

专题命中幻觉与事实性：safety(abstract)

Comments 4 pages, 2 tables and 3 figures

2502.09278 2025-02-26 cs.CV 50%

ConsistentDreamer: View-Consistent Meshes Through Balanced Multi-View Gaussian Optimization

Onat Şahin, Mohammad Altillawi, George Eskandar, Carlos Carbone, Ziyuan Liu

专题命中幻觉与事实性：alignment(abstract)

Comments Manuscript accepted by Pattern Recognition Letters. Project Page: https://onatsahin.github.io/ConsistentDreamer/

Journal ref Pattern Recognition Letters 190 (2025), 118-125

2502.06288 2025-02-25 cs.CV 50%

Enhancing Ground-to-Aerial Image Matching for Visual Misinformation Detection Using Semantic Segmentation

Emanuele Mule, Matteo Pannacci, Ali Ghasemi Goudarzi, Francesco Pro, Lorenzo Papa, Luca Maiano, Irene Amerini

专题命中幻觉与事实性：trustworthy(abstract)

Comments 9 pages, 4 figures. Accepted to AI4MFDD 2025 workshop at WACV 2025

2410.04780 2025-02-19 cs.CV 50%

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality

Guanyu Zhou, Yibo Yan, Xin Zou, Kun Wang, Aiwei Liu, Xuming Hu

专题命中幻觉与事实性：alignment(abstract)

Comments Accepted by The Thirteenth International Conference on Learning Representations (ICLR 2025)

2502.11721 2025-02-18 cs.IR 50%

Enhancing Recommendation Explanations through User-Centric Refinement

Jingsen Zhang, Zihang Tian, Xueyang Feng, Xu Chen

专题命中幻觉与事实性：alignment(abstract)

2502.06019 2025-02-11 cs.CV 50%

Noise is an Efficient Learner for Zero-Shot Vision-Language Models

Raza Imam, Asif Hanif, Jian Zhang, Khaled Waleed Dawoud, Yova Kementchedjhieva, Mohammad Yaqub

专题命中幻觉与事实性：alignment(abstract)

Comments Our code is available at https://github.com/Razaimam45/TNT

2310.08704 2025-01-13 econ.GN q-fin.EC 50%

How Does Artificial Intelligence Improve Human Decision-Making? Evidence from the AI-Powered Go Program

Sukwoong Choi, Hyo Kang, Namil Kim, Junsik Kim

专题命中幻觉与事实性：alignment(abstract)

2404.13945 2024-12-24 cs.SE 50%

How Multi-Modal LLMs Reshape Visual Deep Learning Testing? A Comprehensive Study Through the Lens of Image Mutation

Liwen Wang, Yuanyuan Yuan, Ao Sun, Zongjie Li, Pingchuan Ma, Daoyuan Wu, Shuai Wang

专题命中幻觉与事实性：alignment(abstract)

2411.11919 2024-12-03 cs.CV 50%

VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation

Ruiyang Zhang, Hu Zhang, Zhedong Zheng

专题命中幻觉与事实性：safety(abstract)

2411.07842 2024-11-13 cs.ET 50%

Sparsity-Aware Optimization of In-Memory Bayesian Binary Neural Network Accelerators

Prabodh Katti, Bashir M. Al-Hashimi, Bipin Rajendran

专题命中幻觉与事实性：safety(abstract)

1. 幻觉与事实性 1756 篇

Evaluating explainable AI for deep learning-based network intrusion detection system alert classification

HJRNO: Hamilton-Jacobi Reachability with Neural Operators

A Systematic Mapping Study on Software Architecture for AI-based Mobility Systems

LLM-powered Query Expansion for Enhancing Boundary Prediction in Language-driven Action Localization

Deep Learning-Based BMD Estimation from Radiographs with Conformal Uncertainty Quantification

Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models

DYNUS: Uncertainty-aware Trajectory Planner in Dynamic Unknown Environments

Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models

Paragraph-to-Image Generation with Information-Enriched Diffusion Model

Optical aberrations in autonomous driving: Physics-informed parameterized temperature scaling for neural network uncertainty calibration

Automating Nanoindentation: Optimizing Workflows for Precision and Accuracy

StoryGPT-V: Large Language Models as Consistent Story Visualizers

Interpretable Locomotion Prediction in Construction Using a Memory-Driven LLM Agent With Chain-of-Thought Reasoning

Multi-Agent Reinforcement Learning for Decentralized Reservoir Management via Murmuration Intelligence

FRAP: Faithful and Realistic Text-to-Image Generation with Adaptive Prompt Weighting

Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding

AI-driven Uncertainty Quantification & Multi-Physics Approach to Evaluate Cladding Materials in a Microreactor

Solving the enigma: Enhancing faithfulness and comprehensibility in explanations of deep networks

Conformal forecasting for surgical instrument trajectory

Robust Long-Range Perception Against Sensor Misalignment in Autonomous Vehicles

Open-Source Retrieval Augmented Generation Framework for Retrieving Accurate Medication Insights from Formularies for African Healthcare Workers

ConsistentDreamer: View-Consistent Meshes Through Balanced Multi-View Gaussian Optimization

Enhancing Ground-to-Aerial Image Matching for Visual Misinformation Detection Using Semantic Segmentation

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality

Enhancing Recommendation Explanations through User-Centric Refinement

Noise is an Efficient Learner for Zero-Shot Vision-Language Models

How Does Artificial Intelligence Improve Human Decision-Making? Evidence from the AI-Powered Go Program

How Multi-Modal LLMs Reshape Visual Deep Learning Testing? A Comprehensive Study Through the Lens of Image Mutation

VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation

Sparsity-Aware Optimization of In-Memory Bayesian Binary Neural Network Accelerators