arXivDaily arXiv每日学术速递 周一至周五更新

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。

共收录 1740 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 幻觉与事实性 1740 篇

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)

详情

展开后加载摘要…

URL PDF HTML 收藏
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)

详情

展开后加载摘要…

URL PDF HTML 收藏
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)

详情

展开后加载摘要…

URL PDF HTML 收藏
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)

详情

展开后加载摘要…

URL PDF HTML 收藏
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

详情

展开后加载摘要…

URL PDF HTML 收藏
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

详情

展开后加载摘要…

URL PDF HTML 收藏
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

详情

展开后加载摘要…

URL PDF HTML 收藏
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)

详情

展开后加载摘要…

URL PDF HTML 收藏
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)

详情

展开后加载摘要…

URL PDF HTML 收藏
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

详情

展开后加载摘要…

URL PDF HTML 收藏
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)

详情

展开后加载摘要…

URL PDF HTML 收藏
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)

详情

展开后加载摘要…

URL PDF HTML 收藏
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)

详情

展开后加载摘要…

URL PDF HTML 收藏
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)

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.18953 2024-09-30 cs.CV cs.RO 50%

UniCal: Unified Neural Sensor Calibration

Ze Yang, George Chen, Haowei Zhang, Kevin Ta, Ioan Andrei Bârsan, Daniel Murphy, Sivabalan Manivasagam, Raquel Urtasun

专题命中 幻觉与事实性 :alignment(abstract)

Comments ECCV 2024. Project page: https://waabi.ai/unical/

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.00359 2024-09-05 physics.app-ph 50%

Inverse identification framework for cohesive zone model incorporating failure mode based on multi-island genetic algorithm

Tianxiang Shi, Miao Pang, Yangyang Wang, Yongqiang Zhang

专题命中 幻觉与事实性 :alignment(abstract)

Journal ref engineering-fracture-mechanics 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.00865 2024-09-04 cond-mat.mtrl-sci 50%

Scalable Crystal Structure Relaxation Using an Iteration-Free Deep Generative Model with Uncertainty Quantification

Ziduo Yang, Yi-Ming Zhao, Xian Wang, Xiaoqing Liu, Xiuying Zhang, Yifan Li, Qiujie Lv, Calvin Yu-Chian Chen, Lei Shen

专题命中 幻觉与事实性 :trustworthy(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.02669 2024-08-29 physics.plasm-ph 50%

Multi-objective Bayesian optimization for design of Pareto-optimal current drive profiles in STEP

Theodore Brown, Stephen Marsden, Vignesh Gopakumar, Alexander Terenin, Hong Ge, Francis Casson

专题命中 幻觉与事实性 :safety(abstract)

Comments 6 pages, 4 figures. Submitted to IEEE Transactions on Plasma Science, October 2023. Revised version submitted 7th February 2024

Journal ref IEEE Transactions on Plasma Science (2024)

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.02703 2024-08-08 physics.med-ph physics.app-ph physics.ins-det 50%

Self-calibrating Intelligent OCT-SLO System

Mayank Goswami

专题命中 幻觉与事实性 :alignment(abstract)

Comments 20 Pages, 11 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.10615 2024-07-16 physics.flu-dyn 50%

Physics Based & Machine Learning Methods For Uncertainty Estimation In Turbulence Modeling

Minghan Chu

专题命中 幻觉与事实性 :safety(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.02311 2024-06-28 eess.IV cs.CV 50%

Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentation

Yidong Zhao, Joao Tourais, Iain Pierce, Christian Nitsche, Thomas A. Treibel, Sebastian Weingärtner, Artur M. Schweidtmann, Qian Tao

专题命中 幻觉与事实性 :trustworthy(abstract)

Comments Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://melba-journal.org/2024:011

Journal ref Machine.Learning.for.Biomedical.Imaging. 2 (2024)

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.16621 2024-05-17 physics.chem-ph 50%

Uncertainty quantification by direct propagation of shallow ensembles

Matthias Kellner, Michele Ceriotti

专题命中 幻觉与事实性 :trustworthy(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.10193 2024-04-17 cs.CV 50%

Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering

Zaid Khan, Yun Fu

专题命中 幻觉与事实性 :safety(abstract)

Comments CVPR 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.07275 2024-04-12 stat.AP 50%

Certification of MPC-based zonal controller security properties using accuracy-aware machine learning proxies

Pierre Houdouin, Manuel Ruiz, Patrick Panciatici

专题命中 幻觉与事实性 :safety(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.11797 2024-03-19 astro-ph.CO 50%

Machine Learning LSST 3x2pt analyses -- forecasting the impact of systematics on cosmological constraints using neural networks

Supranta S. Boruah, Tim Eifler, Vivian Miranda, Elyas Farah, Jay Motka, Elisabeth Krause, Xiao Fang, Paul Rogozenski, The LSST Dark Energy Science Collaboration

专题命中 幻觉与事实性 :alignment(abstract)

Comments 16 pages, 10 Figures, To be submitted to PRD. Comments welcome

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.08825 2024-03-11 cs.CV 50%

From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models

Dongsheng Jiang, Yuchen Liu, Songlin Liu, Jin'e Zhao, Hao Zhang, Zhen Gao, Xiaopeng Zhang, Jin Li, Hongkai Xiong

专题命中 幻觉与事实性 :alignment(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.17622 2024-02-28 cs.CV cs.RO 50%

Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modeling

David S. W. Williams, Matthew Gadd, Paul Newman, Daniele De Martini

专题命中 幻觉与事实性 :safety(abstract)

Comments Accepted for publication at 2024 IEEE International Conference on Robotics and Automation (ICRA)

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.06968 2024-02-27 cs.CV 50%

Hallucination Augmented Contrastive Learning for Multimodal Large Language Model

Chaoya Jiang, Haiyang Xu, Mengfan Dong, Jiaxing Chen, Wei Ye, Ming Yan, Qinghao Ye, Ji Zhang, Fei Huang, Shikun Zhang

专题命中 幻觉与事实性 :alignment(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.13261 2024-02-22 physics.ins-det nucl-ex 50%

AI Assisted Experiment Control and Calibration

Thomas Britton, Michael Goodrich, Naomi Jarvis, Torri Jeske, Nikhil Kalra, David Lawrence, Diana McSpadden

专题命中 幻觉与事实性 :safety(abstract)

Comments 68 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2401.01461 2024-01-04 cs.CV 50%

Efficient Hybrid Zoom using Camera Fusion on Mobile Phones

Xiaotong Wu, Wei-Sheng Lai, YiChang Shih, Charles Herrmann, Michael Krainin, Deqing Sun, Chia-Kai Liang

专题命中 幻觉与事实性 :alignment(abstract)

Comments Accepted to SIGGRAPH Asia 2023 (ACM TOG). Project website: https://www.wslai.net/publications/fusion_zoom

详情

展开后加载摘要…

URL PDF HTML 收藏