检索结果-内蒙古大学图书馆

Retrieval-Augmented Fine-Tuning for Improving Retrieve-and-Edit Based Assertion Generation

IEEE Transactions on Software engineering 2025年第5期51卷 1591-1614页

作者： Li, Hongyan Sun, Weifeng Yan, Meng Xu, Ling Li, Qiang Zhang, Xiaohong Zhang, Hongyu Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing400044 China Chongqing University School of Big Data and Software Engineering Chongqing400044 China

Unit Testing is crucial in software development and maintenance, aiming to verify that the implemented functionality is consistent with the expected functionality. A unit test is composed of two parts: a test prefix, which drives the unit under test to a particular state, and a test assertion, which determines what the expected behavior is under that state. To reduce the effort of conducting unit tests manually, Yu et al. proposed an integrated approach (integration for short), combining information retrieval with a deep learning-based approach to generate assertions for test prefixes, and obtained promising results. In our previous work, we found that the overall performance of integration is mainly due to its success in retrieving assertions. Moreover, integration is limited to specific types of edit operations and struggles to understand the semantic differences between the retrieved focal-test (focal-test includes a test prefix and a unit under test) and the input focal-test. Based on these insights, we then proposed a retrieve-and-edit approach named EDITAS to learn the assertion edit patterns to improve the effectiveness of assertion generation in our prior study. Despite being promising, we find that the effectiveness of EDITAS can be further improved. Our analysis shows that: ① The editing ability of EDITAS still has ample room for improvement. Its performance degrades as the edit distance between the retrieval assertion and ground truth increases. Specifically, the average accuracy of EDITAS is 12.38% when the edit distance is greater than 5. ② EDITAS lacks a fine-grained semantic understanding of both the retrieved focal-test and the input focal-test themselves, which leads to many inaccurate token modifications. In particular, an average of 25.57% of the incorrectly generated assertions that need to be modified are not modified, and an average of 6.45% of the assertions that match the ground truth are still modified. Thanks to pre-trained models employing

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Generalize Audio Deepfake Algorithm Recognition via Attribution Enhancement

Generalize Audio Deepfake Algorithm Recognition via Attribut...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Zhigang Ye, Dengpan Li, Jingyang Deng, Jiacheng Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China

ISBN: (纸本)9798350368741

The development of voice cloning techniques has made forgery audios indistinguishable, posing an urgency to trace their sources. Many existing works focus on improving identification accuracy for audio deepfake algorithm recognition. However, most methods ignore the impact of complex information in audio signals on attribution. In this paper, we propose an audio deepfake attribution enhancement (ADAE) strategy, which aims to magnify the fingerprints of generation styles by removing the speaker information. This is achieved through an information disentangle block with an extra speaker encoder. In addition, we propose the FakeSource dataset, a novel audio deepfake algorithm recognition dataset that contains 25 different voice cloning algorithms, to address the constraint of data scarcity. Experiments on the FakeSource dataset demonstrate that ADAE improves the performance of unseen algorithm detection. We also assess ADAE on a more challenging training-free task which shows competitive performance. © 2025 IEEE.

关键词： Audio deepfake algorithm recognition feature enhancement representation disentangle

来源：评论

学校读者我要写书评

暂无评论

Harnessing Dimensional Contrast and Information Compensation for Sentence Embedding Enhancement

Harnessing Dimensional Contrast and Information Compensation...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： He, Kang Ding, Yuzhe Li, Bobo Wang, Haining Li, Fei Teng, Chong Ji, Donghong Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China

ISBN: (纸本)9798350368741

Unsupervised sentence embedding learning excels through positive sample construction and instance-level contrastive learning (ICL). However, this approach can lead to over-compression and dimensional contamination from noisy data augmentation and unconstrained ICL processes. To mitigate these issues, we propose a novel enhancement method, MSSE, which incorporates an Information Compensation Mechanism (ICM) and a Dimensional-Level Contrastive Learning Mechanism (DCM). ICM, inspired by the information bottleneck principle, prevents excessive compression in representation learning. DCM constrains ICL and minimizes information leakage across dimensions. Experimental results show that MSSE surpasses existing competitive baselines across seven STS tasks, including unsupervised and few-shot scenarios. The source code is available at https://***/Hekang001/MSSE. © 2025 IEEE.

关键词： contrastive learning natural language processing Sentence embedding unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

NCRE: A Benchmark for Document-level Nominal Compound Relation Extraction 31

NCRE: A Benchmark for Document-level Nominal Compound Relati...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Cao, Jincheng Li, Bobo Liu, Jiang Ji, Donghong Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China

ISBN: (纸本)9798891761964

Entity and relation extraction is a conventional task in the field of information extraction. Existing work primarily focuses on detecting specific relations between entities, often constrained to particular fields and lacking general applicability. In response, we propose a novel task: nominal compound relation extraction (NCRE), which concentrates on abstract and broadly applicable relation extraction between noun phrases. This task diverges significantly from traditional entity and relation extraction in two key respects. Firstly, our task involves general nominal compounds rather than named entities, which are longer and encompass a broader scope, presenting significant challenges for extraction. Secondly, relation extraction in NCRE demands an in-depth understanding of context to detect abstract relations. We manually annotate a high-quality Chinese dataset for the NCRE task and develop a model incorporating the rotary position-enhanced word pair (RoWP) detection schema. Experimental results demonstrate the efficiency of our RoWP model over previous baselines, while the suboptimal F1 scores indicate that NCRE remains a challenging task. Our code and data are available at https://***/yeecjc/NCRE. © 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

3DGCformer: 3-Dimensional Graph Convolutional transformer for multi-step origin–destination matrix forecasting

引用

Applied Intelligence 2025年第6期55卷 1-18页

作者： Huang, Yiou Deng, Hao Zhao, Shengjie School of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Shanghai China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai China

Forecasting Human mobility is of great significance in the simulation and control of infectious diseases like COVID-19. To get a clear picture of potential future outbreaks, it is necessary to forecast multi-step Origin–Destination (OD) matrices for a relatively long period in the future. However, multi-step Origin–Destination Matrix Forecasting (ODMF) is a non-trivial problem. First, previous ODMF models only forecast the OD matrix for the next time-step, and they cannot perform well on long-term multi-step forecasts due to error accumulation. Second, many ODMF methods capture spatial and temporal dependencies with separate modules, which is insufficient to model spatio-temporal correlations in the time-varying OD matrix sequence. To address the challenges in multi-step ODMF, we propose 3-Dimensional Graph Convolutional Transformer (3DGCformer). As an enhancement of the original 3DGCN, we propose a novel Origin–Destination Feature Propagation (ODFP) rule between 3DGCN layers and integrate 2 3DGCNs with different spatio-temporal graphs and corresponding feature propagation rules to model the formation of OD flows in a more comprehensive way. For multi-step forecasts, 3DGCformer uses Transformer to capture long-term global temporal dependency, and adapt its decoder using labeled tokens to avoid error accumulation and improve time efficiency. To avoid information loss as the number of regions increases, we propose a patch embedding approach to convert data from 3DGCNs to the Transformer module. We perform extensive experiments on 4 real-world human mobility datasets, and the results show that our proposed model outperforms the state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Transferable and Robust Dynamic Adversarial Attack against Object Detection Models

引用

IEEE Internet of Things Journal 2025年第11期12卷 16171-16180页

作者： Wang, Xinxin Chen, Jing Zhang, Zijun He, Kun Wu, Zongru Du, Ruiying Li, Qiao Liu, Gongshen Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan430072 China Shanghai Jiao Tong University Department of Electronic Information and Electrical Engineering Shanghai201100 China

Object detection models have been widely deployed in physical world applications, and they are vulnerable to adversarial attacks. However, most adversarial attacks are implemented in a white-box setting, and under ideal shooting conditions such as fixed distances and angles, and thus have limited attack success rate (ASR) in practice. In this paper, we present a transferable and robust dynamic adversarial attack where the adversarial patches can be printed on or attached to non-rigid objects such as clothes. We develop a cascade module with a momentum-based technique to optimize adversarial patches against various object detection models, achieving better transferability of the patches in a black-box setting. We also develop a strategy of distance-Adaptive patch generation and employ perspective transformation to enhance the robustness of patches. To evaluate the attack performance, we conduct extensive experiments on seven mainstream object detection models at different distances and angles. The results show that our method can achieve an average ASR of 69.85%, which is 3.27 times that of the baseline method at 3 meters. © 2014 IEEE.

关键词： Object detection Computational modeling Closed box Robustness Adaptation models Trusted computing Information security Aerospace engineering Proposals Aerodynamics

来源：评论

学校读者我要写书评

暂无评论

Research on a closed-form solution for safe burial depth range (SDB-RS) of hard rock compressed air energy storage chambers based on no plastic zone criterion

引用

Geomechanics and Geophysics for Geo-Energy and Geo-Resources 2025年第1期11卷 1-19页

作者： Zhao, Cheng Sun, Zeyuan Luo, Qinyuan Qian, Yuan Niu, Jialun Wei, Chao Xing, Jinquan Department of Geotechnical Engineering Tongji University Shanghai200092 China Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education Tongji University Shanghai200092 China Key Laboratory of Geotechnical Mechanics and Engineering of Ministry of Water Resources Changjiang River Scientific Research Institute Hubei Wuhan430010 China

Determining the safe burial depth is crucial for ensuring the long-term stability of compressed air energy storage chambers throughout their operational cycle. This study proposes a safe burial depth solution based on elastic and elastoplastic theories, with the safety criterion being the prevention of plastic zone formation in the surrounding rock. An approximate method is used to calculate the boundary of the plastic zone, and a closed-form safe burial depth range solution is determined by ensuring that the plastic zone remains contained within the chamber boundary. The study demonstrates that both overly shallow and overly deep burial depths can result in the formation of plastic zones, whereas no plastic zone occurs in the surrounding rock when the burial depth is within the range solution. The validation through comparison with previous physical model experiments and numerical simulation methods proves the effectiveness of the solution. The study further reveals that the range of safe burial depths is wider and more suitable for air storage when the lateral pressure coefficient is closer to 1 and the shear strength of the surrounding rock is higher. The solution is applicable to surrounding rocks of Class II and above, and can be quickly solved using the maximum air pressure determined by engineering requirements and the geomechanical parameters of the rock mass obtained from geotechnical investigations. The solution provides high computational efficiency and accuracy and offers significant engineering value for site selection and the design of burial depth in CAES chambers. © The Author(s) 2025.

关键词： Burial depth CAES chambers Closed-form solution Elastic–plastic theory Numerical simulation SBD-RS

来源：评论

学校读者我要写书评

暂无评论

RRHF-V: Ranking Responses to Mitigate Hallucinations in Multimodal Large Language Models with Human Feedback 31

RRHF-V: Ranking Responses to Mitigate Hallucinations in Mult...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Chen, Guoqing Zhang, Fu Lin, Jinghao Lu, Chenglong Cheng, Jingwei School of Computer Science and Engineering Northeastern University China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China

ISBN: (纸本)9798891761964

Multimodal large language models (MLLMs) demonstrate strong capabilities in multimodal understanding, reasoning, and interaction but still face the fundamental limitation of hallucinations, where they generate erroneous or fabricated information. To mitigate hallucinations, existing methods annotate pair-responses (one non-hallucination vs one hallucination) using manual methods or GPT-4V, and train alignment algorithms to improve the correspondence between images and text. More critically, an image description often involve multiple dimensions (e.g., object attributes, posture, and spatial relationships), making it challenging for the model to comprehensively learn multidimensional information from pair-responses. To this end, in this paper, we propose RRHF-V, which is the first using rank-responses (one non-hallucination vs multiple ranking hallucinations) to mitigate multimodal hallucinations. Instead of using pair-responses to train the model, RRHF-V expands the number of hallucinatory responses, so that the responses with different scores in a rank-response enable the model to learn rich semantic information across various dimensions of the image. Further, we propose a scene graph-based approach to automatically construct rank-responses in a cost-effective and automatic manner. We also design a novel training objective based on rank loss and margin loss to balance the differences between hallucinatory responses within a rank-response, thereby improving the model's image comprehension. Experiments on two MLLMs of different sizes and four widely used benchmarks demonstrate that RRHF-V is effective in mitigating hallucinations and outperforms the DPO method based on pair-responses. © 2025 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SGMEA: Structure-Guided Multimodal Entity Alignment 31

SGMEA: Structure-Guided Multimodal Entity Alignment

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Cheng, Jingwei Guo, Mingxiao Zhang, Fu School of Computer Science and Engineering Northeastern University China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China

ISBN: (纸本)9798891761964

Multimodal Entity Alignment (MMEA) aims to identify equivalent entities across different multimodal knowledge graphs (MMKGs) by integrating structural information, entity attributes, and visual data, thereby promoting knowledge sharing and deep multimodal data integration. However, existing methods often overlook the deeper connections between multimodal data. They primarily focus on the interactions between neighboring entities in the structural modality while neglecting the interactions between entities in the visual and attribute modalities. To address this, we propose a structure-guided multimodal entity alignment method (SGMEA), which prioritizes structural information from knowledge graphs to enhance the visual and attribute modalities. By fusing multimodal representations, SGMEA improves the accuracy of entity alignment. Experimental results demonstrate that SGMEA achieves state-of-the-art performance across multiple datasets, validating its effectiveness and superiority in practical applications. © 2025 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

CE-DA: Custom Embedding and Dynamic Aggregation for Zero-Shot Relation Extraction 31

CE-DA: Custom Embedding and Dynamic Aggregation for Zero-Sho...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Fu Liu, He Li, Zehan Cheng, Jingwei School of Computer Science and Engineering Northeastern University China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China

ISBN: (纸本)9798891761964

Zero-shot Relation Extraction (ZSRE) aims to predict novel relations from sentences with given entity pairs, where the relations have not been encountered during training. Prototype-based methods, which achieve ZSRE by aligning the sentence representation and the relation prototype representation, have shown great potential. However, most existing works focus solely on improving the quality of prototype representations, neglecting sentence representations, and lacking interaction between different types of relation side information. In this paper, we propose a novel ZSRE framework named CE-DA, which includes two modules: Custom Embedding and Dynamic Aggregation. We employ a two-stage approach to obtain customized embeddings of sentences. In the first stage, we train a sentence encoder through unsupervised contrastive learning, and in the second stage, we highlight the potential relations between entities in sentences using carefully designed entity emphasis prompts to further enhance sentence representations. Additionally, our dynamic aggregation method assigns different weights to different types of relation side information through a learnable network to enhance the quality of relation prototype representations. In contrast to traditional methods that treat the importance of all side information equally, our dynamic aggregation method further strengthens the interaction between different types of relation side information. Our method demonstrates competitive performance across various metrics on two ZSRE datasets. © 2025 Association for Computational Linguistics.

关键词： Embeddings

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：