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 1756 信号源:cs.CL, cs.AI, cs.CY, cs.LG

1. 幻觉与事实性 1756 篇

2505.23792 2025-06-02 cs.CR cs.AI 57%

Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things

Kai Li, Conggai Li, Xin Yuan, Shenghong Li, Sai Zou, Syed Sohail Ahmed, Wei Ni, Dusit Niyato, Abbas Jamalipour, Falko Dressler, Ozgur B. Akan

机构 * School of Electrical Engineering and Computer Science, TU Berlin(柏林技术大学电气与计算机工程学院) Real-Time and Embedded Computing Systems Research Centre (CISTER)(实时与嵌入式计算系统研究中心) Data61, CSIRO(数据61,澳大利亚联邦科学与工业研究组织) School of Computer Science and Engineering, the University of New South Wales(新南威尔士大学计算机科学与工程学院) State Key Laboratory of Public Big Data, College of Big Data and Information Engineering, Guizhou University(公共大数据国家重点实验室,贵州大学大数据与信息工程学院) Department of Computer Engineering, Qassim University(科威特大学计算机工程系) College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院) Division of Electrical Engineering, Department of Engineering, University of Cambridge(剑桥大学工程系电子工程系) Center for NeXt-Generation Communications (CXC), Koç University(下一代通信中心(CXC),科隆大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.21958 2025-05-29 cs.CL 57%

Resolving Knowledge Conflicts in Domain-specific Data Selection: A Case Study on Medical Instruction-tuning

Qihuang Zhong, Liang Ding, Fei Liao, Juhua Liu, Bo Du, Dacheng Tao

机构 * Department of Gastroenterology, Renmin Hospital, Wuhan University(消化内科,仁医医院,武汉大学) School of Computer Science, Wuhan University(计算机学院,武汉大学) School of Computer Science, Faculty of Engineering, The University of Sydney(计算机学院,工程学院,悉尼大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.20903 2025-05-28 cs.CL 57%

Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?

Ziming Wang, Zeyu Shi, Haoyi Zhou, Shiqi Gao, Qingyun Sun, Jianxin Li

机构 * SKLCCSE, School of Computer Science and Engineering, Beihang University(SKLCCSE,计算机科学与工程学院,北航) School of Software, Beihang University(软件学院,北航) Zhongguancun Laboratory, Beijing(中关村实验室,北京)

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

Comments Accepted to ACL2025 Main; The code will be released soon

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.20880 2025-05-28 cs.CL 57%

MSA at SemEval-2025 Task 3: High Quality Weak Labeling and LLM Ensemble Verification for Multilingual Hallucination Detection

Baraa Hikal, Ahmed Nasreldin, Ali Hamdi

机构 * Faculty of Computer Science, MSA University(计算机科学学院,MSA大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.04615 2025-05-28 cs.CL 57%

HalluCounter: Reference-free LLM Hallucination Detection in the Wild!

Ashok Urlana, Gopichand Kanumolu, Charaka Vinayak Kumar, Bala Mallikarjunarao Garlapati, Rahul Mishra

机构 * IIIT Hyderabad(IIIT海得拉巴) TCS Research, Hyderabad, India(TCS研究, 海得拉巴, 印度) University of Oslo, Norway(奥斯陆大学)

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

Comments 30 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.19511 2025-05-27 cs.CL 57%

Causal Distillation: Transferring Structured Explanations from Large to Compact Language Models

Aggrey Muhebwa, Khalid K. Osman

机构 * Stanford University(斯坦福大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.08739 2025-05-27 cs.LG q-bio.QM 57%

Bayesian Comparisons Between Representations

Heiko H. Schütt

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17520 2025-05-26 cs.AI 57%

Optimizing Retrieval-Augmented Generation for Electrical Engineering: A Case Study on ABB Circuit Breakers

Salahuddin Alawadhi, Noorhan Abbas

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

Comments 17 pages, 4 figures, published in CSIT Vol. 15, 2025. DOI: 10.5121/csit.2025.150905

Journal ref Computer Science and Information Technology, Vol. 15, 2025, pp. 59-77

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13501 2025-05-21 cs.LG physics.comp-ph 57%

SPIEDiff: robust learning of long-time macroscopic dynamics from short-time particle simulations with quantified epistemic uncertainty

Zequn He, Celia Reina

机构 * Department of Mechanical Engineering and Applied Mechanics University of Pennsylvania(机械工程与应用力学系 费城大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13312 2025-05-20 cs.CL 57%

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection

Zhijie Deng, Chris Yuhao Liu, Zirui Pang, Xinlei He, Lei Feng, Qi Xuan, Zhaowei Zhu, Jiaheng Wei

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州)) UC Santa Cruz(加州大学圣克鲁兹分校) UIUC(伊利诺伊大学香槟分校) Southeast University(东南大学) BIAI, ZJUT(脑科学与类脑智能研究院,浙江大学) D5Data.ai

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.13123 2025-05-20 cs.CV cs.AI 57%

Low-hallucination Synthetic Captions for Large-Scale Vision-Language Model Pre-training

Xinsong Zhang, Yarong Zeng, Xinting Huang, Hu Hu, Runquan Xie, Han Hu, Zhanhui Kang

机构 * Tencent(腾讯)

专题命中 幻觉与事实性 :DPO(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.07309 2025-05-13 cs.LG 57%

Uncertainty Profiles for LLMs: Uncertainty Source Decomposition and Adaptive Model-Metric Selection

Pei-Fu Guo, Yun-Da Tsai, Shou-De Lin

机构 * National Taiwan University(国立台湾大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2301.04709 2025-05-12 cs.AI 57%

Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability

Atticus Geiger, Duligur Ibeling, Amir Zur, Maheep Chaudhary, Sonakshi Chauhan, Jing Huang, Aryaman Arora, Zhengxuan Wu, Noah Goodman, Christopher Potts, Thomas Icard

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.03467 2025-05-07 cs.CL 57%

Uncertainty-Aware Large Language Models for Explainable Disease Diagnosis

Shuang Zhou, Jiashuo Wang, Zidu Xu, Song Wang, David Brauer, Lindsay Welton, Jacob Cogan, Yuen-Hei Chung, Lei Tian, Zaifu Zhan, Yu Hou, Mingquan Lin, Genevieve B. Melton, Rui Zhang

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

Comments 22 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.01487 2025-05-07 cs.AI 57%

FastRM: An efficient and automatic explainability framework for multimodal generative models

Gabriela Ben-Melech Stan, Estelle Aflalo, Man Luo, Shachar Rosenman, Tiep Le, Sayak Paul, Shao-Yen Tseng, Vasudev Lal

机构 * Intel Labs(英特尔实验室) Hugging Face

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.01958 2025-05-06 cs.CV cs.CL 57%

A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models

Liqiang Jing, Guiming Hardy Chen, Ehsan Aghazadeh, Xin Eric Wang, Xinya Du

机构 * University of Texas at Dallas(德克萨斯大学达拉斯分校) University of Massachusetts at Amherst(马萨诸塞大学阿姆赫斯特分校) University of California, Santa Cruz(加州大学圣克鲁兹分校)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.02440 2025-05-06 cs.LG 57%

Artificial Intelligence in Reactor Physics: Current Status and Future Prospects

Ruizhi Zhang, Shengfeng Zhu, Kan Wang, Ding She, Jean-Philippe Argaud, Bertrand Bouriquet, Qing Li, Helin Gong

机构 * School of Mathematical Sciences, Shanghai Key Laboratory of Pure Mathematics and Mathematical Practice, East China Normal University(数学学院、上海纯粹数学与数学实践重点实验室、华东师范大学) Department of Engineering Physics, Tsinghua University(工程物理系、清华大学) Électricité de France, R&D(法国电力公司、研发部门) Électricité de France, DQI(法国电力公司、DQI部门) Science and Technology on Reactor System Design Technology Laboratory, Nuclear Power Institute of China(反应堆系统设计技术实验室、中国核工业集团核电研究院) Paris Elite Institute of Technology, Shanghai Jiao Tong University(巴黎精英技术学院、上海交通大学)

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

Comments 33 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.00094 2025-05-01 cs.LG 57%

Gaussian process surrogate model to approximate power grid simulators -- An application to the certification of a congestion management controller

Pierre Houdouin, Lucas Saludjian

机构 * RTE PARIS, FRANCE(法国巴黎电力公司)

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

Comments 6 pages, 7 figures, conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.18639 2025-04-29 cs.CL 57%

Span-Level Hallucination Detection for LLM-Generated Answers

Passant Elchafei, Mervet Abu-Elkheir

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.18278 2025-04-28 cs.LG stat.ML 57%

A comprehensive review of classifier probability calibration metrics

Richard Oliver Lane

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

Comments 60 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.15582 2025-04-23 cs.LG cs.DS stat.ML 57%

Smooth Calibration and Decision Making

Jason Hartline, Yifan Wu, Yunran Yang

机构 * Northwestern University(西北大学) Shanghai Jiaotong University(上海交通大学)

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

Comments In FORC 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.15226 2025-04-22 cs.RO cs.AI cs.SY eess.SY 57%

A Genetic Fuzzy-Enabled Framework on Robotic Manipulation for In-Space Servicing

Nathan Steffen, Wilhelm Louw, Nicholas Ernest, Timothy Arnett, Kelly Cohen

机构 * University of Cincinnati(克利夫兰大学) Thales Avionics(泰勒斯航空电子)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.14848 2025-04-22 cs.CV cs.AI 57%

Object-Level Verbalized Confidence Calibration in Vision-Language Models via Semantic Perturbation

Yunpu Zhao, Rui Zhang, Junbin Xiao, Ruibo Hou, Jiaming Guo, Zihao Zhang, Yifan Hao, Yunji Chen

机构 * University of Science and Technology of China(中国科学技术大学) SKL of Processors, Institute of Computing Technology, CAS(中国科学院计算技术研究所处理器专项实验室) National University of Singapore(新加坡国立大学) University of Chinese Academy of Sciences(中国科学院大学) University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.14429 2025-04-22 cs.CV cs.AI 57%

ResNetVLLM-2: Addressing ResNetVLLM's Multi-Modal Hallucinations

Ahmad Khalil, Mahmoud Khalil, Alioune Ngom

机构 * University of Windsor(温莎大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.14105 2025-04-22 cs.HC cs.AI 57%

Amplify Initiative: Building A Localized Data Platform for Globalized AI

Qazi Mamunur Rashid, Erin van Liemt, Tiffany Shih, Amber Ebinama, Karla Barrios Ramos, Madhurima Maji, Aishwarya Verma, Charu Kalia, Jamila Smith-Loud, Joyce Nakatumba-Nabende, Rehema Baguma, Andrew Katumba, Chodrine Mutebi, Jagen Marvin, Eric Peter Wairagala, Mugizi Bruce, Peter Oketta, Lawrence Nderu, Obichi Obiajunwa, Abigail Oppong, Michael Zimba, Data Authors

机构 * Google Research USA(谷歌研究美国分公司) Makerere University(Makerere大学) Google Research India(谷歌研究印度) Jommo Kenyatta University Agriculture & Technology(乔姆摩肯雅塔大学农业与技术) Hutzpa Innovations Nigeria(Hutzpa创新尼日利亚) Malawi University of Science & Technology(马拉维科学技术大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.11820 2025-04-17 cs.CV cs.AI 57%

Real-World Depth Recovery via Structure Uncertainty Modeling and Inaccurate GT Depth Fitting

Delong Suzhang, Meng Yang

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.10831 2025-04-16 cs.AI cs.RO 57%

Hallucination-Aware Generative Pretrained Transformer for Cooperative Aerial Mobility Control

Hyojun Ahn, Seungcheol Oh, Gyu Seon Kim, Soyi Jung, Soohyun Park, Joongheon Kim

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.04600 2025-04-08 cs.AI cond-mat.other math-ph math.MP nlin.AO physics.soc-ph 57%

Capturing AI's Attention: Physics of Repetition, Hallucination, Bias and Beyond

Frank Yingjie Huo, Neil F. Johnson

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

Comments Comments welcome to neiljohnson@gwu.edu

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.07497 2025-04-08 cs.LG 57%

On Training-Conditional Conformal Prediction and Binomial Proportion Confidence Intervals

Rudi Coppola, Manuel Mazo

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

Journal ref Transactions on Machine Learning Research (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.02895 2025-04-07 cs.CV cs.AI 57%

UAC: Uncertainty-Aware Calibration of Neural Networks for Gesture Detection

Farida Al Haddad, Yuxin Wang, Malcolm Mielle

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

Comments 12 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏