检索结果-内蒙古大学图书馆

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

作者： Jiatong Li Renjun Hu Kunzhe Huang Yan Zhuang Qi Liu Mengxiao Zhu Xing Shi Wei Lin University of Science and Technology of China China Alibaba Cloud Computing China

ISBN: (纸本)9798331314385

Expert-designed close-ended benchmarks are indispensable in assessing the knowledge capacity of large language models (LLMs). Despite their widespread use, concerns have mounted regarding their reliability due to limited test scenarios and an unavoidable risk of data contamination. To rectify this, we present PertEval, a toolkit devised for in-depth probing of LLMs' knowledge capacity through knowledge-invariant perturbations. These perturbations employ human-like restatement techniques to generate on-the-fly test samples from static benchmarks, meticulously retaining knowledge-critical content while altering irrelevant details. Our toolkit further includes a suite of response consistency analyses that compare performance on raw vs. perturbed test sets to precisely assess LLMs' genuine knowledge capacity. Six representative LLMs are re-evaluated using PertEval. Results reveal significantly inflated performance of the LLMs on raw benchmarks, including an absolute 25.8% overestimation for GPT-4. Additionally, through a nuanced response pattern analysis, we discover that PertEval retains LLMs' uncertainty to specious knowledge, and reveals their potential rote memorization to correct options which leads to overestimated performance. We also find that the detailed response consistency analyses by PertEval could illuminate various weaknesses in existing LLMs' knowledge mastery and guide the development of refinement. Our findings provide insights for advancing more robust and genuinely knowledgeable LLMs. Our code is available at https://***/aigc-apps/PertEval.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Predictive Analysis of Consumer Behavior in Webcasting Bandwagons 24

Machine Learning Based Predictive Analysis of Consumer Behav...

引用

2024 Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence, DEAI 2024

作者： Zhu, Lixing Yang, Xue Jiang, Xue Chen, Shufen Chen, Jie Xiao, Yunqing Guangdong University of Science and Technology Dongguan China Alibaba Cloud Big Data Application College Zhuhai College of Science and Technology Zhuhai China

ISBN: (纸本)9798400717147

This paper addresses the problem of predicting consumer behavior in live webcast banding and explores the application of machine learning algorithms in this field and their effectiveness. The study mainly focuses on the use of two machine learning models, Decision Tree and Random Forest, to analyze and predict consumer purchase behavior in live streaming bandwagon campaigns. By simulating a dataset containing 15,000 records, this study conducted detailed training and testing of the models to evaluate their performance on key metrics such as accuracy, recall, precision and F1 score. The experimental results show that the Random Forest model outperforms the Decision Tree model on all the evaluated metrics, especially on accuracy and F1 score. This finding highlights the advantages of integrated learning methods when dealing with complex datasets. In addition, the feature selection process revealed that live streaming viewing duration, number of interactions, and anchor ratings are key factors influencing consumers' purchasing decisions. The findings of this study provide valuable insights for the optimization of marketing strategies for webcast bandwagons. By understanding the key factors influencing consumer purchasing behavior, e-commerce platforms and companies can more effectively position their target markets and optimize their advertising and product promotion strategies. © 2024 ACM.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Lay CO:Achieving Least Lossy Accuracy for Most Efficient RRAM-Based Deep Neural Network Accelerator via Layer-Centric Co-Optimization

引用

计算机科学技术学报（英文版） 2023年第2期38卷 328-347页

作者： Shao-Feng Zhao Fang Wang Bo Liu Dan Feng Yang Liu Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Cloud Computing and Big Data Institute Henan University of Economics and LawZhengzhou 450001China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Research Institute of Huazhong University of Science and Technology in Shenzhen Shenzhen 518057China School of Computer and Artificial Intelligence Zhengzhou UniversityZhengzhou 450001China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Cloud Computing and Big Data Institute Henan University of Economics and LawZhengzhou 450001China

Resistive random access memory(RRAM)enables the functionality of operating massively parallel dot prod-ucts and ***-based accelerator is such an effective approach to bridging the gap between Internet of Things devices'constrained resources and deep neural networks'tremendous *** to the huge overhead of Analog to Digital(A/D)and digital accumulations,analog RRAM buffer is introduced to extend the processing in analog and in *** analog RRAM buffer offers potential solutions to A/D conversion issues,the energy consumption is still challenging in resource-constrained environments,especially with enormous intermediate data ***,criti-cal concerns over endurance must also be resolved before the RRAM buffer could be frequently used in reality for DNN in-ference *** we propose LayCO,a layer-centric co-optimizing scheme to address the energy and endurance con-cerns altogether while strictly providing an inference accuracy *** relies on two key ideas:1)co-optimizing with reduced supply voltage and reduced bit-width of accelerator architectures to increase the DNN's error tolerance and achieve the accelerator's energy efficiency,and 2)efficiently mapping and swapping individual DNN data to a correspond-ing RRAM partition in a way that meets the endurance *** evaluation with representative DNN models demonstrates that LayCO outperforms the baseline RRAM buffer based accelerator by 27x improvement in energy effi-ciency(over TIMELY-like configuration),308x in lifetime prolongation and 6x in area reduction(over RAQ)while main-taining the DNN accuracy loss less than 1％.

关键词： deep learning accelerator resistive random access memory (RRAM) energy efficiency error tolerance

来源：评论

学校读者我要写书评

暂无评论

Interpretable Composition Attribution Enhancement for Visio-linguistic Compositional Understanding

Interpretable Composition Attribution Enhancement for Visio-...

引用

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

作者： Li, Wei Huang, Zhen Tian, Xinmei Lu, Le Li, Houqiang Shen, Xu Ye, Jieping MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China China Alibaba Cloud China

ISBN: (纸本)9798891761643

Contrastively trained vision-language models such as CLIP have achieved remarkable progress in vision and language representation learning. Despite the promising progress, their proficiency in compositional reasoning over attributes and relations (e.g., distinguishing between "the car is underneath the person" and "the person is underneath the car") remains notably inadequate. We investigate the cause for this deficient behavior is the composition attribution issue, where the attribution scores (e.g., attention scores or GradCAM scores) for relations (e.g., underneath) or attributes (e.g., red) in the text are substantially lower than those for object terms. In this work, we show such issue is mitigated via a novel framework called CAE (Composition Attribution Enhancement). This generic framework incorporates various interpretable attribution methods to encourage the model to pay greater attention to composition words denoting relationships and attributes within the text. Detailed analysis shows that our approach enables the models to adjust and rectify the attribution of the texts. Extensive experiments across seven benchmarks reveal that our framework significantly enhances the ability to discern intricate details and construct more sophisticated interpretations of combined visual and linguistic elements. © 2024 Association for Computational Linguistics.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations

arXiv

引用

arXiv 2024年

作者： Li, Jiatong Hu, Renjun Huang, Kunzhe Zhuang, Yan Liu, Qi Zhu, Mengxiao Shi, Xing Lin, Wei University of Science and Technology of China China Alibaba Cloud Computing China

Expert-designed close-ended benchmarks are indispensable in assessing the knowledge capacity of large language models (LLMs). Despite their widespread use, concerns have mounted regarding their reliability due to limited test scenarios and an unavoidable risk of data contamination. To rectify this, we present PertEval, a toolkit devised for in-depth probing of LLMs’ knowledge capacity through knowledge-invariant perturbations. These perturbations employ human-like restatement techniques to generate on-the-fly test samples from static benchmarks, meticulously retaining knowledge-critical content while altering irrelevant details. Our toolkit further includes a suite of response consistency analyses that compare performance on raw vs. perturbed test sets to precisely assess LLMs’ genuine knowledge capacity. Six representative LLMs are re-evaluated using PertEval. Results reveal significantly inflated performance of the LLMs on raw benchmarks, including an absolute 25.8% overestimation for GPT-4. Additionally, through a nuanced response pattern analysis, we discover that PertEval retains LLMs’ uncertainty to specious knowledge, and reveals their potential rote memorization to correct options which leads to overestimated performance. We also find that the detailed response consistency analyses by PertEval could illuminate various weaknesses in existing LLMs’ knowledge mastery and guide the development of refinement. Our findings provide insights for advancing more robust and genuinely knowledgeable LLMs. Our code is available at https://***/aigc-apps/PertEval. Copyright © 2024, The Authors. All rights reserved.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Instance-adaptive Zero-shot Chain-of-Thought Prompting 38

Instance-adaptive Zero-shot Chain-of-Thought Prompting

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yuan, Xiaosong Shen, Chen Yan, Shaotian Zhang, Xiaofeng Xie, Liang Wang, Wenxiao Guan, Renchu Wang, Ying Ye, Jieping College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering MoE Jilin University China Alibaba Cloud Computing China Shanghai Jiao Tong University China College of Computer Science and Technology Zhejiang University of Technology China College of Software Zhejiang University China

Zero-shot Chain-of-Thought (CoT) prompting emerges as a simple and effective strategy for enhancing the performance of large language models (LLMs) in real-world reasoning tasks. Nonetheless, the efficacy of a singular, task-level prompt uniformly applied across the whole of instances is inherently limited since one prompt cannot be a good partner for all, a more appropriate approach should consider the interaction between the prompt and each instance meticulously. This work introduces an instance-adaptive prompting algorithm as an alternative zero-shot CoT reasoning scheme by adaptively differentiating good and bad prompts. Concretely, we first employ analysis on LLMs through the lens of information flow to detect the mechanism under zero-shot CoT reasoning, in which we discover that information flows from question to prompt and question to rationale jointly influence the reasoning results most. We notice that a better zero-shot CoT reasoning needs the prompt to obtain semantic information from the question, and then the rationale aggregates sufficient information from the question directly and via the prompt indirectly. On the contrary, lacking any of those would probably lead to a bad one. Stem from that, we further propose an instance-adaptive prompting strategy (IAP) for zero-shot CoT reasoning. Experiments conducted with LLaMA-2, LLaMA-3, and Qwen on math, logic, and commonsense reasoning tasks (e.g., GSM8k, MMLU, Causal Judgement) obtain consistent improvement, demonstrating that the instance-adaptive zero-shot CoT prompting performs better than other task-level methods with some curated prompts or sophisticated procedures, showing the significance of our findings in the zero-shot CoT reasoning mechanism. © 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

InstAttention: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference 31

InstAttention: In-Storage Attention Offloading for Cost-Effe...

引用

31st IEEE International Symposium on High Performance Computer Architecture, HPCA 2025

作者： Pan, Xiurui Li, Endian Li, Qiao Liang, Shengwen Shan, Yizhou Zhou, Ke Luo, Yingwei Wang, Xiaolin Zhang, Jie Peking University China University of Electronic Science and Technology of China China Institute of Computing Technology Chinese Academy of Sciences China Huawei Cloud China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology China

ISBN: (纸本)9798331506476

The widespread of Large Language Models (LLMs) marks a significant milestone in generative AI. Nevertheless, the increasing context length and batch size in offline LLM inference escalate the memory requirement of the key-value (KV) cache, which imposes a huge burden on the GPU VRAM, especially for resource-constrained scenarios (e.g., edge computing). Several cost-effective solutions leverage host memory or SSDs to reduce storage costs for offline inference scenarios and improve the throughput. Nevertheless, they suffer from significant performance penalties imposed by intensive KV cache accesses due to limited PCIe bandwidth. To address these issues, we propose InstAttention, a novel LLM inference system that offloads the most performance-critical computation (i.e., attention in decoding phase) and data (i.e., KV cache) parts to Computational Storage Drives (CSDs), which minimize the enormous KV transfer overheads. InstAttention designs a dedicated flashaware in-storage attention engine with KV cache management mechanisms to exploit the high internal bandwidths of CSDs instead of being limited by the PCIe bandwidth. The optimized P2P transmission between GPU and CSDs further reduces data migration overheads. Experimental results demonstrate that for a 13B model using an NVIDIA A6000 GPU, InstAttention improves throughput for long-sequence inference by up to 11.1 ×, compared to existing SSD-based solutions such as FlexGen. © 2025 IEEE.

关键词： Computer graphics equipment

来源：评论

学校读者我要写书评

暂无评论

Interpreting and Improving Large Language Models in Arithmetic Calculation 41

Interpreting and Improving Large Language Models in Arithmet...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Wei Wan, Chaoqun Zhang, Yonggang Cheung, Yiu-Ming Tian, Xinmei Shen, Xu Ye, Jieping University of Science and Technology of China China Alibaba Cloud China Hong Kong Baptist University Hong Kong Institute of Artificial Intelligence Hefei Comprehensive National Science Center China

Large language models (LLMs) have demonstrated remarkable potential across numerous applications and have shown an emergent ability to tackle complex reasoning tasks, such as mathematical ***, even for the simplest arithmetic calculations, the intrinsic mechanisms behind LLMs remains mysterious, making it challenging to ensure *** this work, we delve into uncovering a specific mechanism by which LLMs execute *** comprehensive experiments, we find that LLMs frequently involve a small fraction ( Copyright 2024 by the author(s)

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

Bridge-IF: Learning Inverse Protein Folding with Markov Bridges 38

Bridge-IF: Learning Inverse Protein Folding with Markov Brid...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhu, Yiheng Wu, Jialu Li, Qiuyi Yan, Jiahuan Yin, Mingze Wu, Wei Li, Mingyang Ye, Jieping Wang, Zheng Wu, Jian College of Computer Science & Technology Liangzhu Laboratory Zhejiang University China College of Pharmaceutical Sciences Zhejiang University China Alibaba Cloud Computing China School of Public Health Zhejiang University China School of Artificial Intelligence and Data Science University of Science and Technology of China China The Second Affiliated Hospital Zhejiang University School of Medicine China

Inverse protein folding is a fundamental task in computational protein design, which aims to design protein sequences that fold into the desired backbone structures. While the development of machine learning algorithms for this task has seen significant success, the prevailing approaches, which predominantly employ a discriminative formulation, frequently encounter the error accumulation issue and often fail to capture the extensive variety of plausible sequences. To fill these gaps, we propose Bridge-IF, a generative diffusion bridge model for inverse folding, which is designed to learn the probabilistic dependency between the distributions of backbone structures and protein sequences. Specifically, we harness an expressive structure encoder to propose a discrete, informative prior derived from structures, and establish a Markov bridge to connect this prior with native sequences. During the inference stage, Bridge-IF progressively refines the prior sequence, culminating in a more plausible design. Moreover, we introduce a reparameterization perspective on Markov bridge models, from which we derive a simplified loss function that facilitates more effective training. We also modulate protein language models (PLMs) with structural conditions to precisely approximate the Markov bridge process, thereby significantly enhancing generation performance while maintaining parameter-efficient training. Extensive experiments on well-established benchmarks demonstrate that Bridge-IF predominantly surpasses existing baselines in sequence recovery and excels in the design of plausible proteins with high foldability. The code is available at https://***/violet-sto/Bridge-IF. © 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

Peer-to-Peer International Trade Model Based on Blockchain and Smart Contracts: Theory and Practice of BTLC 2

Peer-to-Peer International Trade Model Based on Blockchain a...

引用

2nd International Conference on Big Data and Privacy computing, BDPC 2024

作者： Yan, Junjie Wang, Wennan Feng, Duanyang Song, Shiyang Li, Chengyifan Application College Zhuhai College of Science and Technology Alibaba Cloud Big Data Zhuhai China Academy of Management Guangdong University of Science and Technology Dongguan China City University of Macau Faculty of Data Science China

ISBN: (纸本)9798350307597

This study focuses on BTLC, a peer-to-peer international trade model based on blockchain and smart contracts, which aims to reform the traditional let- ter of credit process, improve international trade efficiency, reduce costs and improve security. By elaborating the BTLC model, this study demonstrates how blockchain technology as well as smart contract technology can be applied in the field of international trade to effectively solve the problems existing in the tra- ditional letter of credit process, such as high transaction costs due to too many intermediaries, high transaction risks due to an imperfect trust mechanism, and inefficiency in transactions. In addition, this paper further proves the superiority of the BTLC model in theory and practice through empirical research. It provides an in-depth discussion of the potential application and development direction of the model in future research. However, there are still some challenges and lim- itations in the practical application of the BTLC model. These challenges and limitations include the need for further empirical studies to validate the model's effectiveness and the problems faced. These include technical standards, laws and regulations. Therefore, this study suggests that future research directions should focus on the implementation challenges of blockchain technology, as well as the application of blockchain technology in other fields, in order to promote the wide application of blockchain technology in international trade. © 2024 IEEE.

关键词： Smart contract

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：