检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Xu Li, Cheng Chang, Yi Wang, Jindong Wu, Yuan School of Artificial Intelligence Jilin University China Institute of Software CAS China Microsoft Research Asia China Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University China International Center of Future Science Jilin University China

Large Language Models (LLMs) have become integral to a wide spectrum of applications, ranging from traditional computing tasks to advanced artificial intelligence (AI) applications. This widespread adoption has spurred extensive research into LLMs across various disciplines, including the social sciences. Notably, studies have revealed that LLMs possess emotional intelligence, which can be further developed through positive emotional stimuli. This discovery raises an intriguing question: can negative emotions similarly influence LLMs, potentially enhancing their performance? In response to this question, we introduce NegativePrompt, a novel approach underpinned by psychological principles, involving ten specifically designed negative emotional stimuli. We embark on rigorous experimental evaluations of five LLMs including Flan-T5-Large, Vicuna, Llama 2, ChatGPT, and GPT-4, across a set of 45 tasks. The results are revealing: NegativePrompt markedly enhances the performance of LLMs, evidenced by relative improvements of 12.89% in Instruction Induction tasks and 46.25% in BIG-Bench tasks. Moreover, we conduct attention visualization experiments to decipher the underlying mechanisms of NegativePrompt’s influence. Our research contributes significantly to the understanding of LLMs and emotion interaction, demonstrating the practical efficacy of NegativePrompt as an emotion-driven method and offering novel insights for the enhancement of LLMs in real-world applications. The code is available at https://***/wangxu0820/NegativePrompt. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

IdentiBug: Model-Driven Visualization of Bug Reports by Extracting Class Diagram Excerpts

IdentiBug: Model-Driven Visualization of Bug Reports by Extr...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Gelareh Meidanipour Lahijany Manuel Ohrndorf Johannes Zenkert Madjid Fathi Udo Kelte Software Engineering Group University of Siegen Germany Knowledge-Based Systems and Knowledge Management University of Siegen Germany

ISBN: (纸本)9781665442084

Bug reports are essential software artifacts that describe software bugs using natural language. Bug localization tools can help developers to understand the relation between bug reports and a software system. However, most approaches for localizing bugs work with unstructured textual information from the source codes and bug reports. This paper proposes an approach for locating and visualizing bug reports based on class diagrams representing the overall structural design of a software system. Our approach called IdentiBug takes advantage of deep learning techniques to train our bug localization model to predict connections between a bug report and the system’s class diagram. The result is a ranked list of classes from which we extract and rank a list of class diagram excerpts for assisting the developers during bug documentation and localization.

关键词： Location awareness Visualization Schedules Codes Computer bugs Unified modeling language Natural languages

来源：评论

学校读者我要写书评

暂无评论

Instance-adaptive zero-shot chain-of-thought prompting 24

Instance-adaptive zero-shot chain-of-thought prompting

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xiaosong Yuan Chen Shen Shaotian Yan Xiaofeng Zhang Liang Xie Wenxiao Wang Renchu Guan Ying Wang Jieping Ye College of Computer Science and Technology Jilin University and Key Laboratory of Symbolic Computation and Knowledge Engineering MoE Jilin University Alibaba Cloud Computing Shanghai Jiao Tong University College of Computer Science and Technology Zhejiang University of Technology College of Software Zhejiang University

ISBN: (纸本)9798331314385

Zero-shot Chain-of-Thought (CoT) prompting emerges as a simple and effective strategy for enhancing the performance of large language models (LLMs) in real-world reasoning tasks. Nonetheless, the efficacy of a singular, task-level prompt uniformly applied across the whole of instances is inherently limited since one prompt cannot be a good partner for all, a more appropriate approach should consider the interaction between the prompt and each instance meticulously. This work introduces an instance-adaptive prompting algorithm as an alternative zero-shot CoT reasoning scheme by adaptively differentiating good and bad prompts. Concretely, we first employ analysis on LLMs through the lens of information flow to detect the mechanism under zero-shot CoT reasoning, in which we discover that information flows from question to prompt and question to rationale jointly influence the reasoning results most. We notice that a better zero-shot CoT reasoning needs the prompt to obtain semantic information from the question, and then the rationale aggregates sufficient information from the question directly and via the prompt indirectly. On the contrary, lacking any of those would probably lead to a bad one. Stem from that, we further propose an instance-adaptive prompting strategy (IAP) for zero-shot CoT reasoning. Experiments conducted with LLaMA-2, LLaMA-3, and Qwen on math, logic, and commonsense reasoning tasks (e.g., GSM8k, MMLU, Causal Judgement) obtain consistent improvement, demonstrating that the instance-adaptive zero-shot CoT prompting performs better than other task-level methods with some curated prompts or sophisticated procedures, showing the significance of our findings in the zero-shot CoT reasoning mechanism.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Efficient CLIP-Powered Dual-Branch Networks for Source-Free Unsupervised Domain Adaptation

arXiv

引用

arXiv 2024年

作者： Li, Yongguang Cao, Yueqi Li, Jindong Wang, Qi Wang, Shengsheng College of Software Jilin University Changchun130012 China College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China School of Artificial Intelligence Jilin University Changchun130012 China Engineering Research Center of Knowledge-Driven Human-Machine Intelligence Ministry of Education Jilin University Changchun130012 China

Source-free Unsupervised Domain Adaptation (SF-UDA) aims to transfer a model’s performance from a labeled source domain to an unlabeled target domain without direct access to source samples, addressing critical data privacy concerns. However, most existing SF-UDA approaches assume the availability of abundant source domain samples, which is often impractical due to the high cost of data annotation. To address the dual challenges of limited source data and privacy concerns, we introduce a data-efficient, CLIP-powered dual-branch network (CDBN). This architecture consists of a cross-domain feature transfer branch and a target-specific feature learning branch, leveraging high-confidence target domain samples to transfer text features of source domain categories while learning target-specific soft prompts. By fusing the outputs of both branches, our approach not only effectively transfers source domain category semantic information to the target domain but also reduces the negative impacts of noise and domain gaps during target training. Furthermore, we propose an unsupervised optimization strategy driven by accurate classification and diversity, preserving the classification capability learned from the source domain while generating more confident and diverse predictions in the target domain. CDBN achieves near state-of-the-art performance with far fewer source domain samples than existing methods across 31 transfer tasks on seven datasets. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Experience report:investigating bug fixes in machine learning frameworks/libraries

引用

Frontiers of Computer Science 2021年第6期15卷 43-58页

作者： Xiaobing SUN Tianchi ZHOU Rongcun WANG Yucong DUAN Lili BO Jianming CHANG School of Information Engineering Yangzhou UniversityYangzhou 225100China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China Jiangsu Engineering Research Center of Knowledge Management and Intelligent Service Yangzhou University Yangzhou 225127China School of Computer Science and Technology China University of Mining and TechnologyXuzhou 221116China School of Computer Science and Cyberspace Security Hainan UniversityHaikou 570228China

Machine learning(ML)techniques and algorithms have been successfully and widely used in various areas including software engineering *** other software projects,bugs are also common in ML projects and *** order to more deeply understand the features related to bug fixing in ML projects,we conduct an empirical study with 939 bugs from five ML projects by manually examining the bug categories,fixing patterns,fixing scale,fixing duration,and types of *** results show that(1)there are commonly seven types of bugs in ML programs;(2)twelve fixing patterns are typically used to fix the bugs in ML programs;(3)68.80%of the patches belong to micro-scale-fix and small-scale-fix;(4)66.77%of the bugs in ML programs can be fixed within one month;(5)45.90%of the bug fixes belong to corrective activity from the perspective of software ***,we perform a questionnaire survey and send them to developers or users of ML projects to validate the results in our empirical *** results of our empirical study are basically consistent with the feedback from *** findings from the empirical study provide useful guidance and insights for developers and users to effectively detect and fix bugs in MLprojects.

关键词： bug fixing machine learning project empirical study questionnaire survey

来源：评论

学校读者我要写书评

暂无评论

IoT Device Identification via A Bio-Inspired Feature Selection Approach

IoT Device Identification via A Bio-Inspired Feature Selecti...

引用

IEEE International Conference on Communications (ICC)

作者： Boxiong Wang Hui Kang Geng Sun Jiahui Li College of Software Jilin University Changchun China College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China

The rapid development of the Internet-of-Things (IoT) also brings security and other problems. Device identification is a crucial tool for IoT security issues, which can detect and prevent cyber-attacks. Feature selection is an effective data preprocessing technique in IoT device identification, which can improve the performance of classification and reduce computational complexity. In this paper, we propose a novel wrapper feature selection approach based on the improved binary honey badger algorithm (IBHBA) to select features in IoT traffic. Four improved factors are employed in IBHBA to expand the search scope, balance the exploration and exploitation phases, and enhance the search capability. Moreover, a binary mechanism is adopted to make the algorithm more suitable for feature selection in IoT device identification. The experimental results on several real IoT traffic datasets denote that IBHBA outperforms some classical and latest comparison algorithms in the feature selection of IoT device identification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Multi-Task Online Matching in Mobile Crowdsensing: A Snapshot-Based Approach

引用

IEEE Internet of Things Journal 2025年

作者： Wei, Kaimin Zhao, Shiting Chen, Jinpeng Pei, Tingrui Sun, Dezhi Jinan University College of Information Science and Technology China Beijing University of Posts and Telecommunications School of Computer Science National Pilot Software Engineering School China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China Department of Information Science China

With the growing popularity of Mobile Crowdsensing (MCS), online matching has recently attracted considerable attention. However, most previous schemes focused on single-task matching, which limits their practicality in new MCS applications that require multi-task matching. Moreover, most MCS tasks require workers to share locations with the platform, which poses serious privacy concerns. To address this issue, we propose a privacy-preserving multi-task online matching algorithm in a snapshot-based mode (PMS). Specifically, the entire time period is divided into snapshots to reduce the waiting time for newly arrived tasks to be matched. In each snapshot, the planar Laplace-based privacy mechanism is applied to protect worker locations and ensure ε-geo-indistinguishability. Meanwhile, the Minimum-Cost Maximum-Flow (MCMF)-based multi-task matching mechanism is presented to maximize the task completion rate while minimizing the total travel cost. Experiments on real-world datasets demonstrate that PMS achieves superior task completion, reduced travel costs, and improved privacy preservation compared to existing algorithms. © 2014 IEEE.

关键词： Mobile Crowdsensing Multi-task Matching Privacy-Preserving Snapshot

来源：评论

学校读者我要写书评

暂无评论

A novel multi-task learning network for skin lesion classification based on multi-modal clues and label-level fusion

引用

Computers in Biology and Medicine 2024年 175卷 108549-108549页

作者： Lin, Qifeng Guo, Xiaoxin Feng, Bo Guo, Juntong Ni, Shuang Dong, Hongliang Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University 2699 Qianjin Street Changchun130012 China College of Computer Science and Technology Jilin University 2699 Qianjin Street Changchun130012 China College of Software Jilin University 2699 Qianjin Street Changchun130012 China

In this paper, we propose a multi-task learning (MTL) network based on the label-level fusion of metadata and hand-crafted features by unsupervised clustering to generate new clustering labels as an optimization goal. We propose a MTL module (MTLM) that incorporates an attention mechanism to enable the model to learn more integrated, variable information. We propose a dynamic strategy to adjust the loss weights of different tasks, and trade off the contributions of multiple branches. Instead of feature-level fusion, we propose label-level fusion and combine the results of our proposed MTLM with the results of the image classification network to achieve better lesion prediction on multiple dermatological datasets. We verify the effectiveness of the proposed model by quantitative and qualitative measures. The MTL network using multi-modal clues and label-level fusion can yield the significant performance improvement for skin lesion classification. © 2024 Elsevier Ltd

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Neurocomputational Modelling of EEG Connectivity: Links Between Depression, Inflammation, and Gut-Microbiome 17th

Neurocomputational Modelling of EEG Connectivity: Links Betw...

引用

17th International Conference on Brain Informatics, BI 2024

作者： Doborjeh, Zohreh lavin, Daniel Hunter, Kirsty Heym, Nadja Heasman, Bryony Doborjeh, Maryam Kasabov, Nikola Gibson, Glen Sumich, Alexander School of Engineering Computer and Mathematical Sciences Knowledge Engineering and Discovery Research Institute Auckland University of Technology Auckland New Zealand School of Population Health Faculty of Medical and Health Sciences The University of Auckland Auckland New Zealand Department of Sport Science School of Science and Technology Nottingham Trent University Nottingham United Kingdom NTU Psychology School of Social Sciences Nottingham Trent University Nottingham United Kingdom School of Software Engineering Dalian University Dalian China Institute for Information and Communication Technologies Bulgarian Academy of Sciences Sofia Bulgaria Department of Food and Nutritional Sciences The University of Reading Whiteknights Reading United Kingdom Department of Psychology and Neuroscience Auckland University of Technology Auckland New Zealand

ISBN: (纸本)9789819632930

The immune and enteric systems have been implicated in psychopathology, including depressive disorders. However, the precise neurocognitive mechanisms remain unclear. The present study uses Brain-Inspired Spiking Neural Network (SNN) technique to model electroencephalographic (EEG) data as a function of gut-microbiota, inflammation, and depressive symptoms. Forty-two participants (nonclinical cohort) were assessed for Bacteroides-Prevotella (BAC) colonization in faecal samples, Interleukin 6 (IL-6) in peripheral blood, depressive symptoms (self-report of cognitive and non-cognitive symptoms) and brain function (resting state EEG). SNN models were applied to EEG data to generate connection weight values across scalp regions. Connection weights were visualized as a function of 1) depression;2) inflammation;3) gut microbiome. Lower depression and higher BAC were associated with higher frontal connection weights (cognitive depression = bilateral, non-cognitive and BAC = left hemisphere only). Lower cognitive depression and lower IL-6 were associated with higher posterior connection weights. The SNN models achieved higher accuracy for theta and alpha EEG sub-bands, highlighting their relevance in differentiating between groups. These findings emphasize the potential of SNNs in predicting parameters from brain functional connectivity data and developing targeted diagnostic and intervention strategies. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Hybrid features and semantic reinforcement network for image forgery detection

Hybrid features and semantic reinforcement network for image...

引用

作者： Chen, Haipeng Chang, Chaoqun Shi, Zenan Lyu, Yingda College of Computer Science and Technology Jilin University Changchun130012 China College of Software Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Public Computer Education and Research Center Jilin University Changchun130012 China

Image forgery detection focuses more on tampering regions than image content of semantic segmentation, it is revealed that wealthier features need to be learned. Moreover, insufficient semantic information causes low efficiency of forgery detection. To address these issues, we propose a hybrid features and semantic reinforcement network (HFSRNet) for image forgery detection, which is an encoding and decoding based network. Specifically, long-short term memory with resampling features has been applied to capture traces from the image patches for finding manipulating artifacts. Consolidated features extracted from rotating residual units are further leveraged to amplify the discrepancy between un-tampered and tampered regions. We then hybridize features from them through a concatenation to further incorporate spatial co-occurrence of these two modalities. In addition, for achieving the semantic consistency between two same level features associated by across layers, semantic reinforcement is implemented on the decoding stage. HFSRNet is an end-to-end architecture that handles multiple types of image forgery including copy-move, splicing, removal. Experiments on three standard image manipulation datasets (NIST16, COVERAGE and CASIA) demonstrate that HFSRNet obtains state-of-the-art performance compared to existing models and baselines. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Semantics

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：