检索结果-内蒙古大学图书馆

Diluie: constructing diverse demonstrations of in-context learning with large language model for unified information extraction

引用

Neural Computing and Applications 2024年第22期36卷 13491-13512页

作者： Guo, Qian Guo, Yi Zhao, Jin Department of Computer Science and Engineering East China University of Science and Technology Shanghai200237 China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai200433 China

Large language models (LLMs) have demonstrated promising in-context learning capabilities, especially with instructive prompts. However, recent studies have shown that existing large models still face challenges in specific information extraction (IE) tasks. Moreover, it could have more effectively utilized various prompts such as instruction tuning, diverse demonstrations of in-context learning, and long-range token sequences for assisting language modeling in understanding context. In this study, we propose DILUIE, a unified information extraction framework based on in-context learning with diverse demonstration examples. DILUIE is encoded with an EVA attention mechanism and incremental encoding technology. Based on the constructed diverse demonstrations, we expand the size of instances efficiently in both instruction tuning and in-context learning to gain insights into the potential benefits of utilizing diverse information extraction datasets. To deepen the understanding of context, we further design three auxiliary tasks to assist in aligning contextual semantics. Experimental results demonstrate that DILUIE achieves 2.23 and 2.53% improvements in terms of Micor-/Macor-F1 on average relative to the current state-of-the-art baseline, which also significantly outperforms the GPT-3.5-turbo in zero-shot settings, and the average token length of achieving the best performance over tasks is around 15k. Furthermore, we observe that in-context learning shows enhanced performance when provided with more demonstrations during multiple-shot instruction tuning (8 k). Additionally, increasing the length of instructions (10 k) can result in a more substantial improvement in the upper limits of scaling for in-context learning. Code is available on https://***/Phevos75/DILUIE. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Enhancement Methods for Chiral Optical Signals by Tailoring Optical Fields and Nanostructures

引用

Engineering 2025年第2期45卷 25-43页

作者： Hanqing Cai Liangliang Gu Haifeng Hu Qiwen Zhan School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai 200093China Zhangjiang Laboratory Shanghai 201204China Shanghai Key Laboratory of Modern Optical System University of Shanghai for Science and TechnologyShanghai 200093China

The unique property of chirality is widely used in various *** the past few decades,a great deal of research has been conducted on the interactions between light and matter,resulting in significant technical advancements in the precise manipulation of light field *** this review,which focuses on current chiral optics research,we introduce the fundamental theory of chirality and highlight the latest achievements in enhancing chiral signals through artificial nano-manufacturing technology,with a particular focus on mechanisms such as light scattering and Mie resonance used to amplify chiral *** providing an overview of enhanced chiral signals,this review aims to provide researchers with an indepth understanding of chiral phenomena and its versatile applications in various domains.

关键词： Mie scattering Optical chirality Circular dichroism Orbital angular momentum Bound states in the continuum Nonlinear optics

来源：评论

学校读者我要写书评

暂无评论

SimSpark: Interactive Simulation of Social Media Behaviors

引用

Proceedings of the ACM on Human-computer Interaction 2025年第2期9卷 1-32页

作者： Lin, Ziyue Shan, Yi Gao, Lin Jia, Xinghua Chen, Siming School of Data Science Fudan University China Shanghai Key Laboratory of Data Science China

Understanding user behaviors on social media has garnered significant scholarly attention, enhancing our comprehension of how virtual platforms impact society and empowering decision-makers. Simulating social media behaviors provides a robust tool for capturing the patterns of social media behaviors, testing hypotheses, and predicting the effects of various interventions, ultimately contributing to a deeper understanding of social media environments. Moreover, it can overcome difficulties associated with utilizing real data for analysis, such as data accessibility issues, ethical concerns, and the complexity of processing large and heterogeneous datasets. However, researchers and stakeholders need more flexible platforms to investigate different user behaviors by simulating different scenarios and characters, which is not possible yet. Therefore, this paper introduces SimSpark, an interactive system including simulation algorithms and interactive visual interfaces which is capable of creating small simulated social media platforms with customizable characters and social environments. We address three key challenges: generating believable behaviors, validating simulation results, and supporting interactive control for generation and results analysis. A simulation workflow is introduced to generate believable behaviors of agents by utilizing large language models. A visual interface enables real-time parameter adjustment and process monitoring for customizing generation settings. A set of visualizations and interactions are also designed to display the models’ outputs for further analysis. Effectiveness is evaluated through case studies, quantitative simulation model assessments, and expert interviews. © 2025 Copyright held by the owner/author(s).

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Identifying Affected Libraries and Their Ecosystems for Open Source Software Vulnerabilities 24

Identifying Affected Libraries and Their Ecosystems for Open...

引用

44th ACM/IEEE International Conference on Software Engineering, ICSE 2024

作者： Wu, Susheng Song, Wenyan Huang, Kaifeng Chen, Bihuan Peng, Xin School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Shanghai China

ISBN: (纸本)9798400702174

Software composition analysis (SCA) tools have been widely adopted to identify vulnerable libraries used in software applications. Such SCA tools depend on a vulnerability database to know affected libraries of each vulnerability. However, it is labor-intensive and error prone for a security team to manually maintain the vulnerability database. While several approaches adopt extreme multi-label learning to predict affected libraries for vulnerabilities, they are practically ineffective due to the limited library labels and the unawareness of ecosystems. To address these problems, we first conduct an empirical study to assess the quality of two fields, i.e., affected libraries and their ecosystems, for four vulnerability databases. Our study reveals notable inconsistency and inaccuracy in these two fields. Then, we propose HOLMES to identify affected libraries and their ecosystems for vulnerabilities via a learning-to-rank technique. The key idea of HOLMES is to gather various evidences about affected libraries and their ecosystems from multiple sources, and learn to rank a pool of libraries based on their relevance to evidences. Our extensive experiments have shown the effectiveness, efficiency and usefulness of HOLMES © 2024 ACM.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Linking Adaptive Structure Induction and Neuron Filtering: A Spectral Perspective for Aspect-based Sentiment Analysis 30

Linking Adaptive Structure Induction and Neuron Filtering: A...

引用

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

作者： Niu, Hao Wang, Maoyi Xiong, Yun Yang, Biao Jia, Xing Guo, Zhonglei Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9782493814104

Recently, it has been discovered that incorporating structure information (e.g., dependency trees) can improve the performance of aspect-based sentiment analysis (ABSA). The structure information is often obtained from off-the-shelf parsers, which are sub-optimal and unwieldy. Therefore, adaptively inducing task-specific structures is helpful in resolving this issue. In this work, we concentrate on adaptive graph structure induction for ABSA and explore the impact of neuron-level manipulation from a spectral perspective on structure induction. Specifically, we consider word representations from PLMs (pre-trained language models) as node features and employ a graph learning module to adaptively generate adjacency matrices, followed by graph neural networks (GNNs) to capture both node features and structural information. Meanwhile, we propose the Neuron Filtering (NeuLT), a method to conduct neuron-level manipulations on word representations in the frequency domain. We conduct extensive experiments on three public datasets to observe the impact of NeuLT on structure induction and ABSA. The results and further analysis demonstrate that performing neuron-level manipulation through NeuLT can shorten Aspects-sentiment Distance of induced structures and be beneficial to improve the performance of ABSA. The effects of our method can achieve or come close to SOTA (state-of-the-art) performance. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

High-precision Online Log Parsing with Large Language Models 24

High-precision Online Log Parsing with Large Language Models

引用

46th International Conference on Software Engineering: Companion, ICSE-Companion 2024

作者： Chen, Xiaolei Shi, Jie Chen, Jia Wang, Peng Wang, Wei Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9798400705021

System logs are vital for diagnosing system failures, with log parsing converting unstructured logs into structured data. Existing methods fall into two categories: non-deep-learning approaches cluster logs based on stats but often miss semantic information, resulting in poor performance. Deep-learning approaches excel at identifying variables and constants but often lack generalizability beyond training data. And they always suffer from low efficiency. This paper proposes a novel LLM-based log parsing approach, named Hooglle, to address these challenges. Leveraging a large language model, Hooglle extracts templates for precise and generalized parsing. To overcome the efficiency issue, we propose a prefix-tree-based full-matching strategy which significantly improves parsing efficiency. Extensive evaluation across real-world datasets showcases Hooglle's superior performance on 16 public benchmark datasets. © 2024 IEEE computer Society. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

A blockchain-enabled wiki framework based on participatory design

引用

Digital Communications and Networks 2022年第6期8卷 995-1004页

作者： Zheng Xu Chaofan Liu Peng Zhang Tun Lu Ning Gu School of Computer Science Fudan UniversityShanghaiChina Shanghai Key Laboratory of Data Science Fudan UniversityShanghaiChina

The 5G mobile Internet facilitates contents generation for online communities and platforms through human-to-human ***,a well-known online community,uses wiki technology to build an encyclopedia through collective intelligence and *** wiki systems adopt a centralized implementation,and while existing studies have optimized the efficiency of the wiki systems'centralized implementation,these systems still suffer from a lot of problems,for example,opacity and *** the years,blockchain has brought a flurry of fervour and decentralization to the system architecture,meanwhile giving users a sense of trust and ***,an innovative blockchain-enabled wiki framework called DecWiki is proposed to build one transparent,truthful,collaborative and autonomous *** several participatory design iterations,we present DecWiki's detailed architecture and its implementation in the form of a smart contract and use the interplanetary file system to complement the big data ***,we use the trusted execution environment to secure sensitive information in the wireless ***,the system overhead and the acceptance of the prototype are *** experiments present its significant performance.

关键词： Blockchain Wiki Participatory design Trusted execution envir onment Smart contract

来源：评论

学校读者我要写书评

暂无评论

Enhancing Entity Relationship Extraction in Dialogue Texts Using Hypergraph and Heterogeneous Graph

引用

Chinese Journal of Electronics 2025年第1期34卷 295-308页

作者： Shunmiao Zhang Siyuan Zheng Degen Huang Dan Li School of Computer Science and Mathematics Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology School of Computer Science and Technology Dalian University of Technology Elsevier

Dialogue-based relation extraction(DialogRE) aims to predict relationships between two entities in dialogue. Current approaches to dialogue relationship extraction grapple with long-distance entity relationships in dialogue data as well as complex entity relationships, such as a single entity with multiple types of connections. To address these issues, this paper presents a novel approach for dialogue relationship extraction termed the hypergraphs and heterogeneous graphs model(HG2G). This model introduces a two-tiered structure, comprising dialogue hypergraphs and dialogue heterogeneous graphs, to address the shortcomings of existing methods. The dialogue hypergraph establishes connections between similar nodes using hyper-edges and utilizes hypergraph convolution to capture multi-level features. Simultaneously, the dialogue heterogeneous graph connects nodes and edges of different types, employing heterogeneous graph convolution to aggregate cross-sentence information. Ultimately, the integrated nodes from both graphs capture the semantic nuances inherent in dialogue. Experimental results on the DialogRE dataset demonstrate that the HG2G model outperforms existing state-of-the-art methods.

关键词： Convolution Aggregates Semantics Feature extraction data mining

来源：评论

学校读者我要写书评

暂无评论

Enhancing Field Tracking and Interprocedural Analysis to Find More Null Pointer Exceptions 31

Enhancing Field Tracking and Interprocedural Analysis to Fin...

引用

31st IEEE International Conference on Software Analysis, Evolution and Reengineering, SANER 2024

作者： Xie, Dongfang Chen, Bihuan Huang, Kaifeng Wang, Yu Pan, Linghao Chen, Zhicheng Peng, Xin Fudan University School of Computer Science Shanghai Key Laboratory of Data Science China

ISBN: (纸本)9798350330663

Null pointer dereference raises Null Pointer Exceptions (NPEs). There are two groups of approaches to detect NPEs. Type-based approaches carry out strict type-based null safety checking. They heavily rely on annotations, and thus produce many false positives. dataflow-based approaches leverage static forward and/or backward dataflow analysis. They mostly have a limited capability in tracking fields and interprocedural analysis, and introduce false positives and false negatives. To address these drawbacks, we propose Wheeljack to detect NPEs for Java. It does not rely on annotations, and hence can work effectively under a lack of annotations. It leverages our novel abstraction of nullness status to enhance field tracking, and our novel invocation analysis (capturing change to return value and side effect of an invocation) to enhance interprocedural analysis. Our evaluation on 28 Java projects has demonstrated that Wheeljack can mostly outperform the four state-of-the-art NPE detectors in recall without sacrificing precision. 5 and 2 new NPEs have been confirmed and fixed by developers after we submit 8 issues. © 2024 IEEE.

关键词： data flow analysis

来源：评论

学校读者我要写书评

暂无评论

Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction 30

Improving Recall of Large Language Models: A Model Collabora...

引用

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

作者： Ding, Zepeng Huang, Wenhao Liang, Jiaqing Yang, Deqing Xiao, Yanghua Shanghai Key Laboratory of Data Science China School of Data Science China School of Computer Science Fudan University China

ISBN: (纸本)9782493814104

Relation triple extraction, which outputs a set of triples from long sentences, plays a vital role in knowledge acquisition. Large language models can accurately extract triples from simple sentences through few-shot learning or fine-tuning when given appropriate instructions. However, they often miss out when extracting from complex sentences. In this paper, we design an evaluation-filtering framework that integrates large language models with small models for relational triple extraction tasks. The framework includes an evaluation model that can extract related entity pairs with high precision. We propose a simple labeling principle and a deep neural network to build the model, embedding the outputs as prompts into the extraction process of the large model. We conduct extensive experiments to demonstrate that the proposed method can assist large language models in obtaining more accurate extraction results, especially from complex sentences containing multiple relational triples. Our evaluation model can also be embedded into traditional extraction models to enhance their extraction precision from complex sentences. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Modeling languages

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：