检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Sun, Yuhong Yin, Zhangyue Guo, Qipeng Wu, Jiawen Qiu, Xipeng Zhao, Hui Software Engineering Institute East China Normal University China School of Computer Science Fudan University China Shanghai AI Laboratory China Shanghai Key Laboratory of Trustworthy Computing Shanghai China

Large language models (LLMs) are highly effective in various natural language processing (NLP) tasks. However, they are susceptible to producing unreliable conjectures in ambiguous contexts called hallucination. This paper presents a new method for evaluating LLM hallucination in Question Answering (QA) based on the unanswerable math word problem (MWP). To support this approach, we innovatively develop a dataset called Unanswerable Math Word Problem (UMWP) which comprises 5200 questions across five categories. We developed an evaluation methodology combining text similarity and mathematical expression detection to determine whether LLM considers the question unanswerable. The results of extensive experiments conducted on 31 LLMs, including GPT-3, InstructGPT, LLaMA, and Claude, demonstrate that in-context learning and reinforcement learning with human feedback (RLHF) training significantly enhance the model's ability to avoid hallucination. We show that utilizing MWP is a reliable and effective approach to assess hallucination. Our code and data are available at https://***/Yuki-Asuuna/UMWP. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Iterative Optimizing Framework for Radiology Report Summarization With ChatGPT

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 4163-4175页

作者： Ma, Chong Wu, Zihao Wang, Jiaqi Xu, Shaochen Wei, Yaonai Liu, Zhengliang Zeng, Fang Jiang, Xi Guo, Lei Cai, Xiaoyan Zhang, Shu Zhang, Tuo Zhu, Dajiang Shen, Dinggang Liu, Tianming Li, Xiang Northwestern Polytechnical University School of Automation Xi'an710072 China University of Georgia School of Computing AthensGA30602 United States Northwestern Polytechnical University School of Computer Science Xi'an710072 China Massachusetts General Hospital Department of Radiology BostonMA02114 United States University of Electronic Science and Technology of China Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation School of Life Science and Technology Chengdu611731 China The University of Texas at Arlington Department of Computer Science and Engineering ArlingtonVA76019 United States ShanghaiTech University School of Biomedical Engineering Shanghai201210 China Shanghai United Imaging Intelligence Company Ltd. Department of Research and Development Shanghai200030 China Shanghai Clinical Research and Trial Center Shanghai201210 China

The 'Impression' section of a radiology report is a critical basis for communication between radiologists and other physicians. Typically written by radiologists, this part is derived from the 'Findings' section, which can be laborious and error-prone. Although deep-learning-based models, such as bidirectional encoder representation from transformers (BERT), have achieved promising results in automatic impression generation (AIG), such models often require substantial amounts of medical data and have poor generalization performance. Recently, large language models (LLMs) like Chat Generative Pre-trained Transformer (ChatGPT) have shown strong generalization capabilities and performance, but their performance in specific domains, such as radiology, remains under-investigated and potentially limited. To address this limitation, we propose ImpressionGPT, leveraging the contextual learning capabilities of LLMs through our dynamic prompt and iterative optimization algorithm to accomplish the AIG task. ImpressionGPT initially employs a small amount of domain-specific data to create a dynamic prompt, extracting contextual semantic information closely related to the test data. Subsequently, the iterative optimization algorithm automatically evaluates the output of LLMs and provides optimization suggestions, continuously refining the output results. The proposed ImpressionGPT model achieves superior performance of AIG task on both the Medical Information Mart for Intensive Care - Chest X-ray database (MIMIC-CXR) and Open Access Biomedical Image Search Engine (OpenI) datasets without requiring additional training data or fine-tuning the LLMs. This work presents a paradigm for localizing LLMs that can be applied in a wide range of similar application scenarios, bridging the gap between general-purpose LLMs and the specific language processing needs of various domains. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A deep learning system for predicting time to progression of diabetic retinopathy

引用

NATURE MEDICINE 2024年第2期30卷 358-359页

作者： [Anonymous] Shanghai Belt and Road International Joint Laboratory for Intelligent Prevention and Treatment of Metabolic Disorders Department of Computer Science and Engineering School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Department of Endocrinology and Metabolism Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai Diabetes Institute Shanghai Clinical Center for Diabetes Shanghai China MOE Key Laboratory of AI School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Department of Ophthalmology Huadong Sanatorium Wuxi China Department of Ophthalmology Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Ophthalmology and Visual Sciences The Chinese University of Hong Kong Hong Kong China Singapore Eye Research Institute Singapore National Eye Centre Singapore Singapore Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong China Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong China State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Sun Yat-sen University Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Guangzhou China Department of Ophthalmology Peking Union Medical College Hospital Peking Union Medical College Chinese Academy of Medical Sciences Beijing China Medical Records and Statistics Office Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Geriatrics Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Tech

We developed and validated a deep learning system (termed DeepDR Plus) in a diverse, multiethnic, multi-country dataset to predict personalized risk and time to progression of diabetic retinopathy. We show that DeepDR Plus can be integrated into the clinical workflow to promote individualized intervention strategies for the management of diabetic retinopathy.

关键词： Diabetes complications Machine learning Predictive markers

来源：评论

学校读者我要写书评

暂无评论

Iterative Channel Estimation for OTFS-based LEO-Sat Communication Using Comb-type ZC Sequences

Iterative Channel Estimation for OTFS-based LEO-Sat Communic...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Shi, Haiwei Xing, Wang Zhou, Yiqing Zhang, Yu Zhou, Shuo Shi, Jinglin Institute of Computing Technology Cas State Key Lab of Processors Beijing China ShanghaiTech University School of Information Science and Technology Shanghai201210 China University of Chinese Academy of Sciences Beijing China Tsinghua University Department of Electronic Engineering Beijing100084 China

ISBN: (纸本)9798350351255

In low earth orbit satellite (LEO-Sat) communication systems based on orthogonal time frequency space (OTFS) modulation, existing channel estimation methods usually use high-power pilots, leading to a high peak-to-average power ratio (PAPR). In this paper, we propose a comb-type pilot based frame structure by inserting multiple identical Zadoff-Chu (ZC) sequences along the Doppler dimension. The ZC sequences are arranged at equal intervals in the delay dimension. The power of pilots is consistent with the power of data symbols, which can achieve low PAPR at the transmitter. At the receiver, based on the analyzed power distribution of the correlation function, we derive the power threshold to identify the received pilots. Then, an iterative ZC-sequences based channel estimation algorithm is proposed aided by data detection and interference cancellation. Through iterations, the data interference can be alleviated and estimation accuracy can be improved. Simulation results demonstrate that the proposed scheme can achieve superior channel estimation performance with low PAPR in the time domain. © 2024 IEEE.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

SUNET: Framework, Security, and Privacy

SUNET: Framework, Security, and Privacy

引用

Satellite Internet (SAT-NET), International Conference on

作者： Zhan Xie Liangmin Wang Haiqin Wu Xiaoyu Zhang Liang Wang Haotian Yang School of Cyber Science and Engineering Southeast University Nanjing China Engineering Research Center of BASAM Ministry of Education Southeast University Nanjing China Software Engineering Institute (Shanghai Key Laboratory of Trustworthy Computing) East China Normal University Shanghai China

ISBN: (数字)9798350375176

ISBN: (纸本)9798350387469

SUNet (Satellite-assisted Unmanned-system Network) integrates satellite communication technology, unmanned equipment systems, and ground support facilities. Compared to traditional network system, SUNet has the advantages of flexible deployment and wide communication range. SUNet with cloud services (SUNET) breaks the limitation of satellites processing large-scale data, and integrates a large scope of computing and storage resources in a system. However, SUNET also poses more serious security risks than traditional networks for two reasons: i) the unique network framework, such as highly dynamic topology, unfixed network access points and decentralized control, of SUNET increases security risks, and ii) the rising probability of existing neighbor nodes with quantum computing. This paper firstly introduces the term SUNET from definition and compares SUNET with several related network frameworks. Then we anaylze the security risks, such as untrust between nodes, unauthorized access and quantum computing attack, faced by SUNET. Meanwhile, we illustrate the security requirements and the corresponding solutions, such as authentication, fine-grained authorization and quantum security, in SUNET. Finally, we discuss the security countermeasures and point out the potential future research directions.

关键词： Privacy Satellites Quantum computing Network topology Vehicular ad hoc networks Computer architecture Topology Security Satellite communications Network systems

来源：评论

学校读者我要写书评

暂无评论

Model Checking Quantum Continuous-Time Markov Chains 32

Model Checking Quantum Continuous-Time Markov Chains

引用

32nd International Conference on Concurrency Theory, CONCUR 2021

作者： Xu, Ming Mei, Jingyi Guan, Ji Yu, Nengkun MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Lab of Trustworthy Computing East China Normal University Shanghai China Shanghai Key Lab of Trustworthy Computing East China Normal University Shanghai China State Key Lab of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Centre for Quantum Software and Information Faculty of Engineering and Information Technology University of Technology Sydney Australia

ISBN: (纸本)9783959772037

Verifying quantum systems has attracted a lot of interests in the last decades. In this paper, we initialise the model checking of quantum continuous-time Markov chain (QCTMC). As a real-time system, we specify the temporal properties on QCTMC by signal temporal logic (STL). To effectively check the atomic propositions in STL, we develop a state-of-the-art real root isolation algorithm under Schanuel's conjecture;further, we check the general STL formula by interval operations with a bottom-up fashion, whose query complexity turns out to be linear in the size of the input formula by calling the real root isolation algorithm. A running example of an open quantum walk is provided to demonstrate our method. © Ming Xu, Jingyi Mei, Ji Guan, and Nengkun Yu;.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

Butler Matrix Enabled Multi-Beam Optical Phased Array for Two-Dimensional Beam-Steering 27

Butler Matrix Enabled Multi-Beam Optical Phased Array for Tw...

引用

27th OptoElectronics and Communications Conference/International Conference on Photonics in Switching and computing, OECC/PSC 2022

作者： Zhou, Zuoyu Xu, Weihan Li, Xinhang Lu, Liangjun Chen, Jianping Zhou, Linjie Shanghai Institute for Advanced Communication and Data Science State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Jiao Tong University Shanghai Key Lab of Navigation and Location Services Department of Electronic Engineering Shanghai200240 China SJTU-Pinghu Institute of Intelligent Optoelectronics Pinghu314200 China

We demonstrate a multi-beam optical phased array based on a 4×4 Butler matrix. The device shows the capability of two-dimensional multi-beam steering with a pm 30^{circ}×8^{circ} field-of-view through a shar... 详细信息

ISBN: (数字)9784885523366

ISBN: (纸本)9784885523366

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

SRender: Boosting Neural Radiance Field Efficiency via Sensitivity-Aware Dynamic Precision Rendering

SRender: Boosting Neural Radiance Field Efficiency via Sensi...

引用

IEEE/ACM International Symposium on Microarchitecture (MICRO)

作者： Zhuoran Song Houshu He Fangxin Liu Yifan Hao Xinkai Song Li Jiang Xiaoyao Liang Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350350579

ISBN: (纸本)9798350350586

Neural Radiance Field (NeRF) holds immense promise for generating photo-realistic images and videos. How-ever, the computation and memory demands significantly impede its applicability in real-time tasks such as virtual reality and augmented reality. While accelerators dedicatedly designed for NeRF have emerged, they may not be the optimal solution as they only consider the optimization of full-precision NeRF models, leading to unsatisfactory memory and computation saving. This paper proposes Sensitivity-Aware Dynamic Precision Rendering, abbreviated as SRender, an algorithm-hardware co-design framework that borrows the idea of Adaptive Rendering commonly used in conventional graphics rendering to accelerate the rendering process of NeRF exploiting the fine-grained per-ray and per-point levels sensitivity. The fundamental idea behind SRender is that rays and points with high sensitivity require high-precision data types, while the insensitive rays and points do not, allowing them to be sacrificed for greater acceleration. Accordingly, the algorithm part of SRender dynamically configures the precision of the hash table and the multilayer perceptron (MLP), and the hardware part features a specialized accelerator that exploits such mixed-precision memory access and computation patterns. Specifically, we predict the sensitive rays and points based on low-precision hash encoding and feature computation. Then, we trigger a high-precision rendering again on the sensitive ones to guarantee the rendering quality. The hardware design of SRender includes a sensitivity prediction engine, coarse-then-fine-grained encoding engines, and a recovery engine, which translates the computational saving in the algorithm to real speedup. Using the coarse-then-fine-grained encoding engine, we maximize the data reuse on-chip, thereby reducing the stress of off-chip memory bandwidth. Experiments show that the edge-level SRender can achieve 3.94x and 34.06x speedup over state-of-the-art NeRF

关键词： Sensitivity Heuristic algorithms Rendering (computer graphics) Neural radiance field Prediction algorithms Encoding Hardware System-on-chip Engines Videos

来源：评论

学校读者我要写书评

暂无评论

NC-ALG: Graph-Based Active Learning under Noisy Crowd 40

NC-ALG: Graph-Based Active Learning under Noisy Crowd

引用

40th IEEE International Conference on data engineering, ICDE 2024

作者： Zhang, Wentao Wang, Yexin You, Zhenbang Li, Yang Cao, Gang Yang, Zhi Cui, Bin Center for Machine Learning Research Peking University China Key Lab of High Confidence Software Technologies Peking University China Institute of Advanced Algorithms Research Shanghai China Institute of Computational Social Science Peking University Qingdao China National Engineering Labratory for Big Data Analytics and Applications China TEG Tencent Inc. Department of Data Platform China Beijing Academy of Artificial Intelligence China

ISBN: (纸本)9798350317152

Graph Neural Networks (GNNs) have achieved great success in various data mining tasks but they heavily rely on a large number of annotated nodes, requiring considerable human efforts. Despite the effectiveness of existing GNN-based Active Learning (AL) methods, they assume that the annotated labels are always correct, which is contradictory to the error-prone labeling process in a practical crowdsourcing environment. Besides, due to this impractical assumption, existing works only focus on optimizing the node selection in AL but neglect optimizing the labeling process. Therefore, we present NC-ALG, the first GNN-based AL framework that optimizes both the node selection and node labeling process under a noisy crowd. For node selection, NC-ALG introduces a new measurement to model influence reliability and an effective influence maximization objective to select nodes. For node labeling, NC-ALG significantly reduces the labeling cost by considering the model-predicted labels and the labels of mirror nodes. To the best of our knowledge, this is the first attempt to consider GNN-based AL under the practical noisy crowd. Empirical studies on public datasets demonstrate that NC-ALG significantly outperforms existing methods in terms labeling efficiency. Notably, it only takes NC-ALG one-third of the labeling budget that the competitive baseline GRAIN needs to achieve an accuracy of 70.7 % on PubMed. © 2024 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

BIM: Improving Graph Neural Networks with Balanced Influence Maximization 40

BIM: Improving Graph Neural Networks with Balanced Influence...

引用

40th IEEE International Conference on data engineering, ICDE 2024

作者： Zhang, Wentao Gao, Xinyi Yang, Ling Cao, Meng Huang, Ping Shan, Jiulong Yin, Hongzhi Cui, Bin Peking University Center for Machine Learning Research China Institute of Advanced Algorithms Research Shanghai China National Engineering Labratory for Big Data Analytics and Applications The University of Queensland Australia Peking University Key Lab of High Confidence Software Technologies China Apple Inc. Institute of Computational Social Science Peking University Qingdao China

ISBN: (纸本)9798350317152

The imbalanced data classification problem has aroused lots of concerns from both academia and industry since data imbalance is a widespread phenomenon in many real-world scenarios. Although this problem has been well researched from the view of imbalanced class samples, we further argue that graph neural networks (GNNs) expose a unique source of imbalance from the influenced nodes of different classes of labeled nodes, i.e., labeled nodes are imbalanced in terms of the number of nodes they influenced during the influence propagation in GNNs. To tackle this previously unexplored influence-imbalance issue, we connect social influence maximization with the imbalanced node classification problem and propose balanced influence maximization (BIM). Specifically, BIM greedily assigns the pseudo label to the node which can maximize the number of influenced nodes in GNN training while making the influence of each class more balance. Experimental results on five public datasets demonstrate the effectiveness of our method in relieving the influence-imbalance issue. For example, when training a GCN with an imbalance ratio of 0.1, BIM significantly outperforms the most competitive baseline by 0.6% -9.8% in five public datasets in terms of the F1 score. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：