检索结果-内蒙古大学图书馆

Don’t Ignore the Drive of Curiosity: Rethinking Subtleties Between Universality of Commonsense Knowledge and Excellence of Large Language Models

引用

SN computer science 2024年第6期5卷 798页

作者： Wang, Chao Chen, Tao Liu, Jingping School of Future Technology Shanghai University Shanghai China Institute of Artificial Intelligence Shanghai University Shanghai China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China School of Information Science and Engineering East China University of Science and Technology Shanghai China

Commonsense reasoning is one of the abilities necessary for artificial intelligence to be as intelligent as humans. However, how to make AI understand commonsense has been a problem that has plagued artificial intelligence for more than 60 years. Existing efforts focus more on the means of knowledge acquisition and strive to enrich the capacity of commonsense knowledge (CSK) bases and dimensions of CSK through advanced methods. Unfortunately, this exuberance has obscured a general consideration of CSK, such as how to follow human habits to obtain the most representative knowledge we need to understand the world. In this paper, this representative knowledge is referred to as core CSK. The influence of core CSK is extensive, and it constitutes almost the fundamental element of human life and the most fundamental cognition of the world. Harnessing human curiosity to find solutions to the above problems is an effective and straightforward route. Specifically, we focus on a special corpus to mine core CSK, namely, why-questions. For example, we can harvest “the sky is blue” from “why is the sky blue?”. To this end, we propose a novel method to extract CSK from why-questions, which mainly consist of two modules. The first is a question classification module used to determine whether a question contains CSK. In this module, we propose a classifier based on a one-sided bootstrapping method and design several informative features for the classifier. The second is a crowdsourcing module used to improve the quality of the extracted commonsense. We conduct extensive experiments, and the experimental results show that our method effectively mines CSK from question corpora. Furthermore, statistical analysis demonstrates the feasibility of this curiosity-driven approach, implying that we provide a basic idea for collecting core CSK. Remarkably, today’s outstanding large language models do not have such simple knowledge summarization capabilities, demonstrating the barrier between

关键词： Classification Core Commonsense knowledge Crowdsourcing Curiosity Psychologically

来源：评论

学校读者我要写书评

暂无评论

Detectability of hierarchical communities in networks

引用

Physical Review E 2024年第3期110卷 034306页

作者： Leto Peel Michael T. Schaub Department of Data Analytics and Digitalisation School of Business and Economics Department of Computer Science

We study the problem of recovering a planted hierarchy of partitions in a network. The detectability of a single planted partition has previously been analyzed in detail and a phase transition has been identified below which the partition cannot be detected. Here we show that, in the hierarchical setting, there exist additional phases in which the presence of multiple consistent partitions can either help or hinder detection. Accordingly, the detectability limit for nonhierarchical partitions typically provides insufficient information about the detectability of the complete hierarchical structure, as we highlight with several constructive examples.

关键词： Community structure Complex systems Network structure Patterns in complex systems Block models data analysis

来源：评论

学校读者我要写书评

暂无评论

Phishing Detection Model Integrating URL Characters and HTML Word Semantic Deep Features 4

Phishing Detection Model Integrating URL Characters and HTML...

引用

4th International Conference on Communication Technology and Information Technology, ICCTIT 2024

作者： Meng, Lihui Ma, Zhujuan Zhu, Erzhou Anhui University School of Computer Science and Technology Hefei230601 China Anhui Xinhua University School of Big Data and Artificial Intelligence Hefei230088 China

ISBN: (纸本)9798331528973

Deep learning methods, known for their powerful feature learning and classification capabilities, are widely used in phishing detection. To improve accuracy, this study proposes DPMLF (Deep Learning Phishing Detection Model with Multi-Level Features), which integrates URL character-level and HTML word-level semantic features. DPMLF utilizes character embeddings and parallel convolutional kernels to precisely extract local URL features. For HTML text, it employs word-level embeddings and stacked convolutional layers with dense connections to capture both local and long-range text information. The fully connected layer then fuses these features into a multi-level, fine-grained feature vector for classification. The results of experiments conducted on two public datasets with different scales show that DPMLF is accurate in phishing attack detection. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Building User-oriented Personalized Machine Translator based on User-Generated Textual Content

引用

Proceedings of the ACM on Human-computer Interaction 2022年第CSCW2期6卷 1–26页

作者： Zhang, Peng Guan, Zhengqing Liu, Baoxi Ding, Xianghua Sharon Lu, Tun Gu, Hansu Gu, Ning School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Shanghai China School of Computing Science University of Glasgow Glasgow United Kingdom Seattle United States

Machine Translation (MT) has been a very useful tool to assist multilingual communication and collaboration. In recent years, by taking advantage of the exciting developments of neural networks and deep learning, the accuracy and speed of machine translation have been continuously improved. However, most machine translation methods and systems are data-driven. They tend to select a consensus response represented in training data, while a user's preferred linguistic style, which is important for translation comprehension and user experience, is ignored. For this problem, we aim to build a user-oriented personalized machine translation model in this paper. The model aims to learn each user's linguistic style from the textual content that is generated by her/him (User-Generated Textual Content, UGTC) in social media context and generate personalized translation results utilizing several state-of-The-Art deep learning techniques like Transformer and pre-Training. We also implemented a user-oriented personalized machine translator using Weibo as a case of the source of UGTC to provide a systematical implementation scheme of a user-oriented personalized machine translation system based on our model. The translator was evaluated by automatic evaluation in combination with human evaluation. The results suggest that our model can generate more personalized, natural and lively translation results and enhance the comprehensibility of translation results, which makes its generations more preferred by users versus general translation results. © 2022 ACM.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing data 38

DiffLight: A Partial Rewards Conditioned Diffusion Model for...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Hanyang Jiang, Yang Guo, Shengnan Mao, Xiaowei Lin, Youfang Wan, Huaiyu School of Computer Science and Technology Beijing Jiaotong University China Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing China

The application of reinforcement learning in traffic signal control (TSC) has been extensively researched and yielded notable achievements. However, most existing works for TSC assume that traffic data from all surrounding intersections is fully and continuously available through sensors. In real-world applications, this assumption often fails due to sensor malfunctions or data loss, making TSC with missing data a critical challenge. To meet the needs of practical applications, we introduce DiffLight, a novel conditional diffusion model for TSC under data-missing scenarios in the offline setting. Specifically, we integrate two essential sub-tasks, i.e., traffic data imputation and decision-making, by leveraging a Partial Rewards Conditioned Diffusion (PRCD) model to prevent missing rewards from interfering with the learning process. Meanwhile, to effectively capture the spatial-temporal dependencies among intersections, we design a Spatial-Temporal transFormer (STFormer) architecture. In addition, we propose a Diffusion Communication Mechanism (DCM) to promote better communication and control performance under data-missing scenarios. Extensive experiments on five datasets with various data-missing scenarios demonstrate that DiffLight is an effective controller to address TSC with missing data. The code of DiffLight is released at https://***/lokol5579/DiffLight-release. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Forward Reasoning and Multi-Reward Backward Refinement for Product Review Summarization 30

Multi-Objective Forward Reasoning and Multi-Reward Backward ...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Sun, Libo Wang, Siyuan Han, Meng Lai, Ruofei Zhang, Xinyu Huang, Xuanjing Wei, Zhongyu School of Data Science Fudan University China Huawei Poisson Lab China School of Computer Science Fudan University China Research Institute of Intelligent Complex Systems Fudan University China

ISBN: (纸本)9782493814104

Product review summarization aims to generate a concise summary based on product reviews to facilitate purchasing decisions. This intricate task gives rise to three challenges in existing work: factual accuracy, aspect comprehensiveness, and content relevance. In this paper, we first propose a FB-Thinker framework to improve the summarization ability of LLMs with multi-objective forward reasoning and multi-reward backward refinement. To enable LLM with these dual capabilities, we present two Chinese product review summarization datasets, Product-CSum and Product-CSum-Cross, for both instruction-tuning and cross-domain evaluation. Specifically, these datasets are collected via GPT-assisted manual annotations from an online forum and public datasets. We further design an evaluation mechanism Product-Eval, integrating both automatic and human evaluation across multiple dimensions for product summarization. Experimental results show the competitiveness and generalizability of our proposed framework in the product review summarization tasks. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Product design

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence algorithms for object detection and recognition in video and images

引用

Multimedia Tools and Applications 2025年 1-18页

作者： Dakshinamoorthy, Prabakar Rajaram, Gnanajeyaraman garg, Shruti Murugan, Prabhu Manimaran, A. Sundar, Ramesh Department of Data Science and Business System School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur Chennai India Department of Computer Science Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India Birla Institute of Technology Mesra Ranchi India Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai602105 India Department of Computer Science Engineering Saveetha School Of EngineeringSaveetha Institute of Medical and Technical Sciences Chennai6021055 India Department of Netwoking and Communication School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur Chennai India

The usage of machine learning and deep learning algorithms have necessitated Artificial Intelligence'. AI is aimed at automating things by limiting human interference. It is widely used in IT, healthcare, finance, and agriculture. It is achieved through several deep learning algorithms that reflect the human brain's intelligence. These AI algorithms can be manipulated according to changing needs and improved efficiency. This paper tries to utilize the developments made in AI technology to classify the images and recognize the objects present in them. One widely used AI algorithm is CNN (Convolutional Neural Networks). The CNN is a deep learning-based algorithm that consists of various layers that extract and filters the parameters present in the images. Some additional layers of ResNet50 and the CNN algorithm are used to extract the parameters to improve image recognition accuracy. The image dataset taken for training and testing the proposed model is imageNet. The images are initially processed before sending them to the proposed model. The proposed model is trained, validated, and tested through the images obtained after the initial processing. The same process is repeated several times until getting the maximum accuracy. The accuracy of the proposed model in terms of image recognition is recorded. The obtained results are compared with other image classification algorithms like VGG16 and VGG19. It is concluded that the proposed model outperforms other traditional methods in terms of accuracy. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Faster local solvers for graph diffusion equations 24

Faster local solvers for graph diffusion equations

引用

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

作者： Jiahe Bai Baojian Zhou Deqing Yang Yanghua Xiao The School of Data Science Fudan University The School of Data Science Fudan University and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University

ISBN: (纸本)9798331314385

Efficient computation of graph diffusion equations (GDEs), such as Personalized PageRank, Katz centrality, and the Heat kernel, is crucial for clustering, training neural networks, and many other graph-related problems. Standard iterative methods require accessing the whole graph per iteration, making them time-consuming for large-scale graphs. While existing local solvers approximate diffusion vectors through heuristic local updates, they often operate sequentially and are typically designed for specific diffusion types, limiting their applicability. Given that diffusion vectors are highly localizable, as measured by the participation ratio, this paper introduces a novel framework for approximately solving GDEs using a local diffusion process. This framework reveals the suboptimality of existing local solvers. Furthermore, our approach effectively localizes standard iterative solvers by designing simple and provably sublinear time algorithms. These new local solvers are highly parallelizable, making them well-suited for implementation on GPUs. We demonstrate the effectiveness of our framework in quickly obtaining approximate diffusion vectors, achieving up to a hundred-fold speed improvement, and its applicability to large-scale dynamic graphs. Our framework could also facilitate more efficient local message-passing mechanisms for GNNs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Quantitative Reasoning Skills of Large Language Models through Dimension Perception 40

Enhancing Quantitative Reasoning Skills of Large Language Mo...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Huang, Yuncheng He, Qianyu Liang, Jiaqing Jiang, Sihang Xiao, Yanghua Chen, Yunwen School of Computer Science Shanghai Key Laboratory of Data Science Fudan University China School of Data Science Fudan University China DataGrand Co. LTD. Research Group of Computational and AI Communication Institute for Global Communications and Integrated Media Fudan University China

ISBN: (纸本)9798350317152

Quantities are distinct and critical components of texts that characterize the magnitude properties of entities, providing a precise perspective for the understanding of natural language, especially for reasoning tasks. In recent years, there has been a flurry of research on reasoning tasks based on large language models (LLMs), most of which solely focus on numerical values, neglecting the dimensional concept of quantities with units despite its importance. We argue that the concept of dimension is essential for precisely understanding quantities and of great significance for LLMs to perform quantitative reasoning. However, the lack of dimension knowledge and quantity-related benchmarks has resulted in low performance of LLMs. Hence, we present a framework to enhance the quantitative reasoning ability of language models based on dimension perception. We first construct a dimensional unit knowledge base (DimUnitKB) to address the knowledge gap in this area. We propose a benchmark DimEval consisting of seven tasks of three categories to probe and enhance the dimension perception skills of LLMs. To evaluate the effectiveness of our methods, we propose a quantitative reasoning task and conduct experiments. The experimental results show that our dimension perception method dramatically improves accuracy (43.55%→50.67%) on quantitative reasoning tasks compared to GPT-4. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

AI-Press: A Multi-Agent News Generating and Feedback Simulation System Powered by Large Language Models 31

AI-Press: A Multi-Agent News Generating and Feedback Simulat...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Liu, Xiawei Yang, Shiyue Zhang, Xinnong Kuang, Haoyu Sun, Libo Yang, Yihang Chen, Siming Huang, Xuanjing Wei, Zhongyu School of Data Science Fudan University China Institute of Science and Technology for Brain-Inspired Intelligence Fudan University China School of Computer Science Fudan University China Research Institute of Intelligent Complex Systems Fudan University China

ISBN: (纸本)9798891761988

The rise of various social platforms has transformed journalism. The growing demand for news content has led to the increased use of large language models (LLMs) in news production due to their speed and cost-effectiveness. However, LLMs still encounter limitations in professionalism and ethical judgment in news generation. Additionally, predicting public feedback is usually difficult before news is released. To tackle these challenges, we introduce AI-Press, an automated news drafting and polishing system based on multi-agent collaboration and Retrieval-Augmented Generation. We develop a feedback simulation system that generates public feedback considering demographic distributions. Through extensive quantitative and qualitative evaluations, our system shows significant improvements in news-generating capabilities and verifies the effectiveness of public feedback simulation. ©2025 Association for Computational Linguistics.

关键词： Computational linguistics

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：