检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： He, Qianyu Zeng, Jie He, Qianxi Liang, Jiaqing Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Data Science Fudan University China

ISBN: (纸本)9798891761681

It is imperative for Large language models (LLMs) to follow instructions with elaborate requirements (i.e. Complex Instructions Following). Yet, it remains under-explored how to enhance the ability of LLMs to follow complex instructions with multiple constraints. To bridge the gap, we initially study what training data is effective in enhancing complex constraints following abilities. We found that training LLMs with instructions containing multiple constraints enhances their understanding of complex instructions, especially those with lower complexity levels. Additionally, we further propose methods addressing how to obtain and utilize the effective training data. Finally, we conduct extensive experiments to prove the effectiveness of our methods in terms of overall performance and training efficiency. We also demonstrate that our methods improve models' ability to follow instructions generally and generalize effectively across out-of-domain, in-domain, and adversarial settings, while maintaining general capabilities. The datasets and code are publicly available at https://***/meowpass/FollowComplexInstruction. © 2024 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

Is There a One-Model-Fits-All Approach to Information Extraction? Revisiting Task Definition Biases

Is There a One-Model-Fits-All Approach to Information Extrac...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Huang, Wenhao He, Qianyu Li, Zhixu Liang, Jiaqing Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Data Science Fudan University China

ISBN: (纸本)9798891761681

Definition bias is a negative phenomenon that can mislead models. Definition bias in information extraction appears not only across datasets from different domains but also within datasets sharing the same domain. We identify two types of definition bias in IE: bias among information extraction datasets and bias between information extraction datasets and instruction tuning datasets. To systematically investigate definition bias, we conduct three probing experiments to quantitatively analyze it and discover the limitations of unified information extraction and large language models in solving definition bias. To mitigate definition bias in information extraction, we propose a multi-stage framework consisting of definition bias measurement, bias-aware fine-tuning, and task-specific bias mitigation. Experimental results demonstrate the effectiveness of our framework in addressing definition bias. © 2024 Association for Computational Linguistics.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

RE-SEGNN:recurrent semantic evidence-aware graph neural network for temporal knowledge graph forecasting

引用

science China(Information sciences) 2025年第2期68卷 103-119页

作者： Wenyu CAI Mengfan LI Xuanhua SHI Yuanxin FAN Quntao ZHU Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and Technology

Temporal knowledge graph(TKG) reasoning, has seen widespread use for modeling real-world events, particularly in extrapolation settings. Nevertheless, most previous studies are embedded models, which require both entity and relation embedding to make predictions, ignoring the semantic correlations among different entities and relations within the same timestamp. This can lead to random and nonsensical predictions when unseen entities or relations occur. Furthermore, many existing models exhibit limitations in handling highly correlated historical facts with extensive temporal depth. They often either overlook such facts or overly accentuate the relationships between recurring past occurrences and their current counterparts. Due to the dynamic nature of TKG, effectively capturing the evolving semantics between different timestamps can be *** address these shortcomings, we propose the recurrent semantic evidenceaware graph neural network(RE-SEGNN), a novel graph neural network that can learn the semantics of entities and relations simultaneously. For the former challenge, our model can predict a possible answer to missing quadruples based on semantics when facing unseen entities or relations. For the latter problem, based on an obvious established force, both the recency and frequency of semantic history tend to confer a higher reference value for the current. We use the Hawkes process to compute the semantic trend, which allows the semantics of recent facts to gain more attention than those of distant facts. Experimental results show that RE-SEGNN outperforms all SOTA models in entity prediction on 6 widely used datasets, and 5 datasets in relation prediction. Furthermore, the case study shows how our model can deal with unseen entities and relations.

关键词： knowledge graph reasoning temporal knowledge graph Hawkes process semantic evidence

来源：评论

学校读者我要写书评

暂无评论

Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works

Evaluating Character Understanding of Large Language Models ...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Yuan, Xinfeng Yuan, Siyu Cui, Yuhan Lin, Tianhe Wang, Xintao Xu, Rui Chen, Jiangjie Yang, Deqing School of Data Science Fudan University China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China

ISBN: (纸本)9798891761643

Large language models (LLMs) have demonstrated impressive performance and spurred numerous AI applications, in which role-playing agents (RPAs) are particularly popular, especially for fictional characters. The prerequisite for these RPAs lies in the capability of LLMs to understand characters from fictional works. Previous efforts have evaluated this capability via basic classification tasks or characteristic imitation, failing to capture the nuanced character understanding with LLMs. In this paper, we propose evaluating LLMs' character understanding capability via the character profiling task, i.e., summarizing character profiles from corresponding materials, a widely adopted yet understudied practice for RPA development. Specifically, we construct the CROSS dataset from literature experts and assess the generated profiles by comparing them with ground truth references and evaluating their applicability in downstream tasks. Our experiments, which cover various summarization methods and LLMs, have yielded promising results. These results strongly validate the character understanding capability of LLMs. Resources are available at https://***/Joanna0123/character_profiling. © 2024 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

Boosting Text-to-SQL through Multi-grained Error Identification 31

Boosting Text-to-SQL through Multi-grained Error Identificat...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Xu, Bo Li, Shufei Jing, Hongyu Du, Ming Song, Hui Wang, Hongya Xiao, Yanghua School of Computer Science and Technology Donghua University China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China

ISBN: (纸本)9798891761964

Text-to-SQL is a technology that converts natural language questions into executable SQL queries, allowing users to query and manage relational databases more easily. In recent years, large language models have significantly advanced the development of text-to-SQL. However, existing methods often overlook validation of the generated results during the SQL generation process. Current error identification methods are mainly divided into self-correction approaches based on large models and feedback methods based on SQL execution, both of which have limitations. We categorize SQL errors into three main types: system errors, skeleton errors, and value errors, and propose a multi-grained error identification method. Experimental results demonstrate that this method can be integrated as a plugin into various methods, providing effective error identification and correction capabilities. © 2025 Association for Computational Linguistics.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multimodal Named Entity Recognition through Adaptive Mixup Image Augmentation 31

Enhancing Multimodal Named Entity Recognition through Adapti...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Xu, Bo Jiang, Haiqi Wei, Jie Jing, Hongyu Du, Ming Song, Hui Wang, Hongya Xiao, Yanghua School of Computer Science and Technology Donghua University China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China

ISBN: (纸本)9798891761964

Multimodal named entity recognition (MNER) extends traditional named entity recognition (NER) by integrating visual and textual information. However, current methods still face significant challenges due to the text-image mismatch problem. Recent advancements in text-to-image synthesis provide promising solutions, as synthesized images can introduce additional visual context to enhance MNER model performance. To fully leverage the benefits of both original and synthesized images, we propose an adaptive mixup image augmentation method. This method generates augmented images by determining the mixing ratio based on the matching score between the text and image, utilizing a triplet loss-based Gaussian Mixture Model (TL-GMM). Our approach is highly adaptable and can be seamlessly integrated into existing MNER models. Extensive experiments demonstrate consistent performance improvements, and detailed ablation studies and case studies confirm the effectiveness of our method. © 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

High-speed encrypted traffic classification by using payload features

引用

Digital Communications and Networks 2025年第2期11卷 412-423页

作者： Xinge Yan Liukun He Yifan Xu Jiuxin Cao Liangmin Wang Guyang Xie School of Cyber Science and Engineering Southeast UniversityNanjing 211189China Nanjing Huafei Data Technology Co. Ltd.Nanjing 210019China School of Computer Science and Communication Engineering Jiangsu UniversityZhenjiang 212013China

Traffic encryption techniques facilitate cyberattackers to hide their presence and *** classification is an important method to prevent network ***,due to the tremendous traffic volume and limitations of computing,most existing traffic classification techniques are inapplicable to the high-speed network *** this paper,we propose a High-speed Encrypted Traffic Classification(HETC)method containing two ***,to efficiently detect whether traffic is encrypted,HETC focuses on randomly sampled short flows and extracts aggregation entropies with chi-square test features to measure the different patterns of the byte composition and distribution between encrypted and unencrypted ***,HETC introduces binary features upon the previous features and performs fine-grained traffic classification by combining these payload features with a Random Forest *** experimental results show that HETC can achieve a 94%F-measure in detecting encrypted flows and a 85%–93%F-measure in classifying fine-grained flows for a 1-KB flow-length dataset,outperforming the state-of-the-art comparison ***,HETC does not need to wait for the end of the flow and can extract mass computing *** average time for HETC to process each flow is only 2 or 16 ms,which is lower than the flow duration in most cases,making it a good candidate for high-speed traffic classification.

关键词： Traffic classification Flow analysis Information entropy Machine learning Randomness test

来源：评论

学校读者我要写书评

暂无评论

Blockchain with drug traceability in medical supply chain with Henry gas solubility optimisation algorithm

引用

International Journal of Wireless and Mobile Computing 2025年第2期28卷 135-148页

作者： Devi, P. Yamini Sriramya, P. Department of Computer Science and Engineering Saveetha School of Engineering Thandalam Tamil Nadu Chennai India Department of Data Science Saveetha School of Engineering SIMATS Tamil Nadu Chennai India

The drug traceability model is used for ensuring drug quality and its safety for customers in the medical supply chain. The healthcare supply chain is a complex network, which is susceptible to failures and leakage of information because of cyber security attacks. Hence, this research aims to design a blockchain to perform traceability of drugs using Henry Gas Solubility Optimisation (HGSO). The entities include distributors, wholesalers, retailers, blockchain and patients. This model comprises initialisation, registration, key generation, authentication, drug distribution with traceability and key generation phases. Any exchange of medicines needs the approval of both sender and receiver. The drugs are registered in the blockchain, which then generates a secret key that is obtained using HGSO. The verification and authentication of drugs are performed after the authentication process. The implemented model outperformed with the response time, memory, normalised variance, and privacy of 32.678 sec, 84 MB, 0.958 and 0.958. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： authentication blockchain drug traceability key generation medical supply chain

来源：评论

学校读者我要写书评

暂无评论

Neighbor Library-Aware Graph Neural Network for Third Party Library Recommendation

引用

Tsinghua science and Technology 2023年第4期28卷 769-785页

作者： Ying Jin Yi Zhang Yiwen Zhang School of Artificial Intelligence and Big Data Hefei UniversityHefei 230601China School of Computer Science and Technology Anhui UniversityHefei 230601China

Modern software development has moved toward agile growth and rapid delivery,where developers must meet the changing needs of users *** such a situation,plug-and-play Third-Party Libraries(TPLs)introduce a considerable amount of convenience to ***,selecting the exact candidate that meets the project requirements from the countless TPLs is challenging for *** works have considered setting up a personalized recommender system to suggest TPLs for ***,these approaches rarely consider the complex relationships between applications and TPLs,and are unsatisfactory in accuracy,training speed,and convergence *** this paper,we propose a new end-to-end recommendation model called Neighbor Library-Aware Graph Neural Network(NLA-GNN).Unlike previous works,we only initialize one type of node embedding,and construct and update all types of node representations using Graph Neural Networks(GNN).We use a simplified graph convolution operation to alternate the information propagation process to increase the training efficiency and eliminate the heterogeneity of the app-library bipartite graph,thus efficiently modeling the complex high-order relationships between the app and the *** experiments on large-scale real-world datasets demonstrate that NLA-GNN achieves consistent and remarkable improvements over state-of-the-art baselines for TPL recommendation tasks.

关键词： Third-Party Library(TPL) TPL recommendation Graph Neural Network(GNN) bipartite graph

来源：评论

学校读者我要写书评

暂无评论

Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative data

Capturing Minds, Not Just Words: Enhancing Role-Playing Lang...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Ran, Yiting Wang, Xintao Xu, Rui Yuan, Xinfeng Liang, Jiaqing Yang, Deqing Xiao, Yanghua School of Data Science Fudan University China School of Computer Science Fudan University China

ISBN: (纸本)9798891761681

Role-playing agents (RPA) have been a popular application area for large language models (LLMs), attracting significant interest from both industry and academia. While existing RPAs well portray the characters' knowledge and tones, they face challenges in capturing their minds, especially for small role-playing language models (RPLMs). In this paper, we propose to enhance RPLMs via personality-indicative data. Specifically, we leverage questions from psychological scales and distill advanced RPAs to generate dialogues that grasp the minds of characters. Experimental results validate that RPLMs trained with our dataset exhibit advanced role-playing capabilities for both general and personality-related evaluations. Code and data are available at https://***/alienet1109/RolePersonality. © 2024 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：