检索结果-内蒙古大学图书馆

Are Large Language Models Really Good Logical Reasoners? A comprehensive Evaluation and Beyond

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2025年第4期37卷 1620-1634页

作者： Xu, Fangzhi Lin, Qika Han, Jiawei Zhao, Tianzhe Liu, Jun Cambria, Erik Xi An Jiao Tong Univ Sch Comp Sci & Technol Key Lab Intelligent Networks & Net work Secur Minist Educ Xian 710049 Shaanxi Peoples R China Shaanxi Prov Key Lab Big Data Knowledge Engn Xian 710049 Shaanxi Peoples R China Nanyang Technol Univ Coll Comp & Data Sci Singapore 639798 Singapore

Logical reasoning consistently plays a fundamental and significant role in the domains of knowledge engineering and artificial intelligence. Recently, Large Language Models (LLMs) have emerged as a noteworthy innovation in natural language processing (NLP). However, the question of whether LLMs can effectively address the task of logical reasoning, which requires gradual cognitive inference similar to human intelligence, remains unanswered. To this end, we aim to bridge this gap and provide comprehensive evaluations in this paper. First, to offer systematic evaluations, we select fifteen typical logical reasoning datasets and organize them into deductive, inductive, abductive and mixed-form reasoning settings. Considering the comprehensiveness of evaluations, we include 3 early-era representative LLMs and 4 trending LLMs. Second, different from previous evaluations relying only on simple metrics (e.g., accuracy), we propose fine-level evaluations in objective and subjective manners, covering both answers and explanations, including answer correctness, explain correctness, explain completeness and explain redundancy. Additionally, to uncover the logical flaws of LLMs, problematic cases will be attributed to five error types from two dimensions, i.e., evidence selection process and reasoning process. Third, to avoid the influences of knowledge bias and concentrate purely on benchmarking the logical reasoning capability of LLMs, we propose a new dataset with neutral content. Based on the in-depth evaluations, this paper finally forms a general evaluation scheme of logical reasoning capability from six dimensions (i.e., Correct, Rigorous, Self-aware, Active, Oriented and No hallucination). It reflects the pros and cons of LLMs and gives guiding directions for future works.

关键词： Cognition Benchmark testing Measurement Large language models Self-aware Systematics Redundancy Knowledge engineering Chatbots Accuracy Logical reasoning large language model deductive reasoning inductive reasoning abductive reasoning

来源：评论

学校读者我要写书评

暂无评论

Quantification of part-of-speech relationships for aspect sentiment triplet extraction

引用

JOURNAL OF intelligent INFORMATION SYSTEMS 2025年 1-23页

作者： Wang, Jiacan Liu, Jianhua Ke, Tianci Chen, Kewei Cai, Zijie Xu, Ge Fujian Univ Technol Sch Comp Sci & Math Fuzhou 350118 Fujian Peoples R China Fujian Prov Key Lab Big Data Min & Applicat Fuzhou 350118 Fujian Peoples R China Minjiang Univ Fujian Prov Key Lab Informat Proc & Intelligent Co Fuzhou 350121 Fujian Peoples R China

Aspect Sentiment Triple Extraction (ASTE) is a fine-grained aspect-level sentiment analysis aimed at extracting aspect words, opinion words, and the sentiment polarity between them in text. Existing end-to-end ASTE models tend to ignore information such as the potential lexical relationships between words and their differences in importance, and fail to take full advantage of the interaction between lexical features and dependency features. To address the above problem, we propose a Quantification of Part-of-speech Relationships for Aspect Sentiment Triplet Extraction (QoPR-ASTE). The model first extracts contextual semantic features by combinatorial encoder;then analyzes the connection and dependency between lexical pairs of words to mine potential syntactic information, and assigns weights according to the importance, constructs lexical adjacency weight matrices and dependency type weight matrices, so as to remove the redundant information and strengthen the expression of syntactic features;then extracts the syntactic information by the two-group graphical convolutional network and the syntactic interaction module and fusion;finally, the semantic and syntactic information is fused through the multi-head attention graph transformation module, and the sentence is labeled using word pair relations and decoded to extract the triad. The F1 values of this model on the four public datasets demonstrate an improvement of 0.80%, 1.46%, 0.92%, and 0.78% compared to the PBLUN model, respectively. The experimental results indicate that the model is capable of efficiently mining potential semantic and syntactic information, thereby significantly enhancing the accuracy of triplet extraction.

关键词： Aspect sentiment triplet extraction Part of speech Dependency relationship Graph convolutional network Weight distribution Word pair relationship tagging

来源：评论

学校读者我要写书评

暂无评论

Embedding dynamic graph attention mechanism into Clinical Knowledge Graph for enhanced diagnostic accuracy

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 267卷

作者： Chen, Deng Zhang, Weiwei Ding, Zuohua Zhejiang Sci Tech Univ Sch Comp Sci & Technol Hangzhou 310018 Peoples R China Inst Sci & Tech Informat Zhejiang Prov Hangzhou 310023 Peoples R China Zhejiang Big Data Dev Ctr Key Lab Open Data Zhejiang Prov Hangzhou 310013 Peoples R China Sun Yat Sen Univ Sch Biomed Engn Shenzhen 518107 Peoples R China

Diagnostic accuracy plays a pivotal role in healthcare, directly affecting treatment efficacy and patient outcomes. Errors in diagnosis can result in inappropriate or delayed treatments, exacerbating conditions and escalating costs. Traditional diagnostic approaches often analyze data in isolation, which can lead to potential oversights and inefficiencies stemming from the fragmented nature of healthcare data systems. Clinical Knowledge Graphs (CKGs) offer a solution by integrating diverse data types-including electronic health records, clinical notes, and genomic data-into a dynamic and interconnected framework, thereby facilitating a holistic understanding of patient health. However, CKGs encounter challenges such as maintaining current and accurate information, adapting to new data, and managing computational complexity, which can limit their effectiveness in real-time clinical applications. This paper proposes anew method that incorporates a dynamic graph attention mechanism within a CKG to enhance diagnostic accuracy in healthcare. By unifying various data sources within a graph-based framework and leveraging advanced graph learning techniques, the proposed method addresses the challenges associated with traditional diagnostic models. comparative analyses demonstrate the model's superior performance in both accuracy and efficiency, highlighting its potential for clinical application.

关键词： Clinical Knowledge Graph Global knowledge graph Local knowledge graph Dynamic graph attention Diagnostic model

来源：评论

学校读者我要写书评

暂无评论

Many-to-One Lightweight Batch Authentication key Agreement for Wireless Body Area Networks

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第6期12卷 7225-7239页

作者： Liu, Sanqiang Xie, Dong Li, Zhiyang Chen, Fulong Bian, Weixin Wang, Taochun Anhui Normal Univ Anhui Engn Res Ctr Med Big Data Intelligent Syst Anhui Prov Key Lab Ind Intelligence Data Secur Wuhu 241002 Peoples R China Anhui Normal Univ Sch Comp & Informat Wuhu 241002 Peoples R China

Wireless body area networks (WBANs) are widely used in the medical field, which makes it easier for doctors to gather patients' physiological information to diagnose their physical status. Recently, a variety of lightweight authentication key agreement (AKA) protocols have been proposed for WBANs. However, the computational overhead of the authentication process for most of these protocols increases exponentially when the number of patients increases dramatically. Therefore, to improve the authentication efficiency, a many-to-one, lightweight batch AKA protocol based on the Chinese remainder theorem is proposed, which can realize that cloud server (CS) interacts with the gateway nodes once to obtain multiple session keys with different sensor nodes, so as to achieve the effect that multiple sensor nodes participate in the AKA at the same time. In addition, only hash function, XOR operation, and symmetric encryption are used in the proposed protocol. During the key agreement process, CS can compute the session key between it and the sensor node on demand. Sensor nodes can dynamically join and leave the WBAN, which increases the flexibility of the protocol. We verify the protocol's security using formal security analysis tools, such as the real-or-random model, Burrows-Abadi-Needham logic, and the proverif tool. The experiment and comparison results indicate that the proposed protocol outperforms the other related protocols in terms of efficiency.

关键词： Protocols Security Body area networks Wireless communication Authentication Internet of Things Biomedical monitoring Hash functions Encryption Servers Batch authentication Chinese remainder theorem (CRT) dynamic join and leave flexibility many-to-one

来源：评论

学校读者我要写书评

暂无评论

Hierarchical fine-grained state-aware graph attention network for dialogue state tracking

引用

JOURNAL OF SUPERcompUTING 2025年第5期81卷 1-31页

作者： Liao, Hongmiao Chen, Yuzhong Chen, Deming Xu, Junjie Zhong, Jiayuan Dong, Chen Fuzhou Univ Coll Comp & Data Sci Fuzhou 350108 Fujian Peoples R China Minist Educ Engn Res Ctr Big Data Intelligence Fuzhou 350108 Fujian Peoples R China Fujian Prov Key Lab Network Comp & Intelligent Inf Fuzhou 350108 Fujian Peoples R China

The objective of dialogue state tracking (DST) is to dynamically track information within dialogue states by populating predefined state slots, which enhances the comprehension capabilities of task-oriented dialogue systems in processing user requests. Recently, there has been a growing popularity in using graph neural networks to model the relationships between slots and slots as well as between dialogue and slots. However, these models overlook the relationships between words and phrases in the current turn dialogue and dialogue history. Specific syntactic dependencies (e.g., the object of a preposition) and constituents (e.g., noun phrases) have a higher probability of being the slot values that need to be retrieved at current moment. Neglecting these syntactic dependency and constituent information may cause the loss of potential candidate slot values, thereby limiting the overall performance of DST models. To address this issue, we propose a Hierarchical Fine-grained State Aware Graph Attention Network for Dialogue State Tracking (HFSG-DST). HFSG-DST exploits the syntactic dependency and constituent tree information, such as phrase segmentation and hierarchical structure in dialogue utterances, to construct a relational graph between entities. It then employs a hierarchical graph attention network to facilitate the extraction of fine-grained candidate dialogue state information. Additionally, HFSG-DST designs a Schema-enhanced Dialogue History Selector to select the most relevant turn of dialogue history for current turn and incorporates schema description information for dialogue state tracking. Consequently, HFSG-DST is capable of constructing the dependency tree and constituent tree on noise-free utterances. Experimental results on two public benchmark datasets demonstrate that HFSG-DST outperforms other state-of-the-art models.

关键词： Dialogue state tracking Syntactic information Hierarchical graph attention network Schema enhancement

来源：评论

学校读者我要写书评

暂无评论

Multi-view multi-behavior interest learning network and contrastive learning for multi-behavior recommendation

引用

KNOWLEDGE-BASED SYSTEMS 2024年 305卷

作者： Su, Jieyang Chen, Yuzhong Lin, Xiuqiang Zhong, Jiayuan Dong, Chen Fuzhou Univ Coll Comp & Data Sci Fuzhou 350108 Fujian Peoples R China Minist Educ Engn Res Ctr Big Data Intelligence Fuzhou Peoples R China Fujian Prov Key Lab Network Comp & Intelligent Inf Fuzhou 350108 Fujian Peoples R China

The recommendation system aims to recommend items to users by capturing their personalized interests. Traditional recommendation systems typically focus on modeling target behaviors between users and items. However, in practical application scenarios, various types of behaviors (e.g., click, favorite, purchase, etc.) occur between users and items. Despite recent efforts in modeling various behavior types, multi-behavior recommendation still faces two significant challenges. The first challenge is how to comprehensively capture the complex relationships between various types of behaviors, including their interest differences and interest commonalities. The second challenge is how to solve the sparsity of target behaviors while ensuring the authenticity of information from various types of behaviors. To address these issues, a multi-behavior recommendation framework based on Multi-View Multi-Behavior Interest Learning Network and Contrastive Learning (MMNCL) is proposed. This framework includes a multi-view multi-behavior interest learning module that consists of two submodules: the behavior difference aware submodule, which captures intra-behavior interests for each behavior type and the correlations between various types of behaviors, and the behavior commonality aware submodule, which captures the information of interest commonalities between various types of behaviors. Additionally, a multi-view contrastive learning module is proposed to conduct node self- discrimination, ensuring the authenticity of information integration among various types of behaviors, and facilitating an effective fusion of interest differences and interest commonalities. Experimental results on three real-world benchmark datasets demonstrate the effectiveness of MMNCL and its advantages over other state-of-the-art recommendation models. Our code is available at https://***/sujieyang/MMNCL.

关键词： Multi-behavior recommendation Interest learning network Meta learning Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

RGBT Tracking via Progressive Fusion Transformer With Dynamically Guided Learning

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第9期34卷 8722-8735页

作者： Zhu, Yabin Li, Chenglong Wang, Xiao Tang, Jin Huang, Zhixiang Anhui Univ Key Lab Intelligent Comp & Signal Proc Minist Educ Hefei 230601 Peoples R China Anhui Univ Sch Artificial Intelligence Anhui Prov Key Lab Multimodal Cognit Computat Informat Mat & Intelligent Sensing Lab Anhui Prov Hefei 230601 Peoples R China Anhui Univ Sch Comp Sci & Technol Anhui Prov Key Lab Multimodal Cognit Computat Informat Mat & Intelligent Sensing Lab Anhui Prov Hefei 230601 Peoples R China Anhui Univ Informat Mat & Intelligent Sensing Lab Anhui Prov Ctr Big Data & Populat Hlth Inst Hlth & Medcine Hefei 230601 Peoples R China

Existing Transformer-based RGB-Thermal (RGBT) tracking methods either use cross-attention to fuse the two modalities, or use self-attention and cross-attention to model both modality-specific and modality-sharing information. However, the significant appearance gap between modalities limits the feature representation ability of certain modalities during the fusion process. To address this problem, we propose a novel Progressive Fusion Transformer called ProFormer, which progressively integrates single-modality information into the multimodal representation for robust RGBT tracking. In particular, ProFormer first uses a self-attention module to collaboratively extract the multimodal representation. Then, ProFormer introduces two cross-attention modules to interact it with the features of the dual modalities for enhancing modality-specific information in the multimodal representation. In addition, we propose a dynamically guided learning algorithm that adaptively employs the well-performing branches to guide the learning of other branches, to improve the representation ability of each branch. Extensive experiments demonstrate that our proposed ProFormer achieves a new state-of-the-art performance on RGBT210, RGBT234, LasHeR, and VTUAV datasets.

关键词： RGBT tracking progressive fusion transformer dynamically guided learning

来源：评论

学校读者我要写书评

暂无评论

Multi-label Feature Selection With Missing Features via Implicit label Replenishment and Positive Correlation Feature Recovery

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2025年第4期37卷 2042-2055页

作者： Dai, Jianhua Chen, Wenxiang Qian, Yuhua Hunan Normal Univ Coll Informat Sci & Engn Hunan Prov Key Lab Intelligent Comp & Language Inf Changsha 410081 Peoples R China Shanxi Univ Inst Big Data Sci & Ind Taiyuan 030006 Peoples R China

Multi-label feature selection can effectively solve the curse of dimensionality problem in multi-label learning. Existing multi-label feature selection methods mostly handle multi-label data without missing features. However, in practical applications, multi-label data with missing features exist widely, and most existing multi-label feature selection methods are not directly applicable. Therefore, we propose a feature selection method for multi-label data with missing features. First, we propose a method to extract implicit label information from the feature space to replenish the binary label information. Second, we learn the positive correlation between features to construct a feature correlation recovery matrix to recover missing features. Finally, we design a sparse model-based multi-label feature selection method for processing multi-label data with missing features and prove the convergence of this method. comparative experiments with existing feature selection methods demonstrate the effectiveness of our method.

关键词： Feature extraction Correlation Sparse matrices data mining Manifold learning Matrix decomposition data models Convergence Vectors Training Multi-label feature selection missing features implicit label information sparse model

来源：评论

学校读者我要写书评

暂无评论

Minimizing Response Delay in UAV-Assisted Mobile Edge computing by Joint UAV Deployment and computation Offloading

引用

IEEE TRANSACTIONS ON CLOUD compUTING 2024年第4期12卷 1372-1386页

作者： Zhang, Jianshan Luo, Haibo Chen, Xing Shen, Hong Guo, Longkun Minjiang Univ Sch Comp & Big Data Fujian Prov Key Lab Informat Proc & Intelligent Co Fuzhou 350121 Peoples R China Fuzhou Univ Minist Educ Engn Res Ctr Big Data Intelligence Coll Comp & Data SciFujian Key Lab Network Comp & Fuzhou 350118 Peoples R China Cent Queensland Univ Sch Engn & Technol Brisbane Qld 4000 Australia Fuzhou Univ Sch Math & Stat Fuzhou 350118 Peoples R China

As a promising technique for offloading computation tasks from mobile devices, Unmanned Aerial Vehicle (UAV)-assisted Mobile Edge computing (MEC) utilizes UAVs as computational resources. A popular method for enhancing the quality of service (QoS) of UAV-assisted MEC systems is to jointly optimize UAV deployment and computation task offloading. This imposes the challenge of dynamically adjusting UAV deployment and computation offloading to accommodate the changing positions and computational requirements of mobile devices. Due to the real-time requirements of MEC computation tasks, finding an efficient joint optimization approach is imperative. This paper proposes an algorithm aimed at minimizing the average response delay in a UAV-assisted MEC system. The approach revolves around the joint optimization of UAV deployment and computation offloading through convex optimization. We break down the problem into three sub-problems: UAV deployment, Ground Device (GD) access, and computation tasks offloading, which we address using the block coordinate descent algorithm. Observing the $NP$NP-hardness nature of the original problem, we present near-optimal solutions to the decomposed sub-problems. Simulation results demonstrate that our approach can generate a joint optimization solution within seconds and diminish the average response delay compared to state-of-the-art algorithms and other advanced algorithms, with improvements ranging from 4.70% to 42.94%.

关键词： Autonomous aerial vehicles Optimization Mobile handsets Servers Delays Relays Heuristic algorithms Multi-access edge computing computer architecture Cloud computing Block coordinate descent computation offloading mobile edge computing unmanned aerial vehicle deployment

来源：评论

学校读者我要写书评

暂无评论

MEGCF: Multimodal Entity Graph Collaborative Filtering for Personalized Recommendation

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 2023年第2期41卷 1-27页

作者： Liu, Kang Xue, Feng Guo, Dan Wu, Le Li, Shujie Hong, Richang Hefei Univ Technol Sch Comp Sci & Informat Engn Key Lab Knowledge Engn Big Data Intelligent Interconnected Syst Lab Anhui Prov 485 Danxia Rd Hefei 230601 Anhui Peoples R China Hefei Univ Technol Sch Software Key Lab Knowledge Engn Big Data Intelligent Interconnected Syst Lab Anhui Prov 485 Danxia Rd Hefei 230601 Anhui Peoples R China

In most E-commerce platforms, whether the displayed items trigger the user's interest largely depends on their most eye-catching multimodal content. Consequently, increasing efforts focus on modeling multimodal user preference, and the pressing paradigm is to incorporate complete multimodal deep features of the items into the recommendation module. However, the existing studies ignore the mismatch problem between multimodal feature extraction (MFE) and user interest modeling (UIM). That is, MFE and UIM have different emphases. Specifically, MFE is migrated from and adapted to upstream tasks such as image classification. In addition, it is mainly a content-oriented and non-personalized process, while UIM, with its greater focus on understanding user interaction, is essentially a user-oriented and personalized process. Therefore, the direct incorporation of MFE into UIM for purely user-oriented tasks, tends to introduce a large number of preference-independent multimodal noise and contaminate the embedding representations in UIM. This paper aims at solving the mismatch problem between MFE and UIM, so as to generate high-quality embedding representations and better model multimodal user preferences. Towards this end, we develop a novel model, multimodal entity graph collaborative filtering, short for MEGCF. The UIM of the proposed model captures the semantic correlation between interactions and the features obtained from MFE, thus making a better match between MFE and UIM. More precisely, semantic-rich entities are first extracted from the multimodal data, since they are more relevant to user preferences than other multimodal information. These entities are then integrated into the user-item interaction graph. Afterwards, a symmetric linear Graph Convolution Network (GCN) module is constructed to perform message propagation over the graph, in order to capture both high-order semantic correlation and collaborative filtering signals. Finally, the sentiment information fr

关键词： Collaborative filtering semantic correlation multimodal user preference multimodal semantic entity collaborative signal graph convolutional network sentiment analysis

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：