检索结果-内蒙古大学图书馆

On the Capacity of Citation Generation by Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Qian, Haosheng Fan, Yixing Zhang, Ruqing Guo, Jiafeng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

Retrieval-augmented generation (RAG) appears as a promising method to alleviate the "hallucination" problem in large language models (LLMs), since it can incorporate external traceable resources for response generation. The essence of RAG in combating the hallucination issue lies in accurately attributing claims in responses to the corresponding retrieved documents. However, most of existing works focus on improving the quality of generated responses from the LLM, while largely overlooked its ability to attribute sources accurately. In this study, we conduct a systematic analysis about the capabilities of LLMs in generating citations within response generation, and further introduce a novel method to enhance their citation generation abilities. Specifically, we evaluate both the correctness and citation quality for seven widely-used LLMs on two benchmark datasets. Meanwhile, we introduce new citation evaluation metrics to eliminate the over-penalization of unnecessary and excessive citations in existing metrics. Furthermore, we propose a Generate-then-Refine method that completes relevant citations and removes irrelevant ones without altering the response text. The results on WebGLM-QA, ASQA and ELI5 datasets show that our method substantially improves the quality of citations in responses generated by LLMs. Copyright © 2024, The Authors. All rights reserved.

关键词：

In-field testing of NAND flash storage: Why and how?

学校读者我要写书评

暂无评论

In-field testing of NAND flash storage: Why and how?

2012 IEEE 21st Asian Test Symposium, ATS 2012

作者： Hu, Yu Gu, Xinli Li, Xiaowei State Key Laboratory of Computer Architecture Institute of Computing Technology CAS Beijing China North America Network Division Huawei Technologies Co. Ltd Santa Clara United States

ISBN: (纸本)9780769548760

NAND Flash memories have rapidly emerged as a storage class memory such as SSD, CF Card, SD Card. Due to its distinct operation mechanisms, NAND Flash memory suffers from erase/program endurance, data retention and program/read disturbance problems. In this work, we propose an in-field testing technique which takes some pages in a block as predictors. We will discuss the proposed technique in detail in the poster session. © 2012 IEEE.

关键词： NAND circuits

Accurate Recovery of Internet Traffic data: A Sequential Tensor Completion Approach

学校读者我要写书评

暂无评论

Accurate Recovery of Internet Traffic Data: A Sequential Ten...

作者： Xie, Kun Wang, Lele Wang, Xin Xie, Gaogang Wen, Jigang Zhang, Guangxing Cao, Jiannong Zhang, Dafang College of Computer Science and Electronics Engineering Hunan University Changsha410006 China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100864 China Department of Electrical and Computer Engineering State University of New York at Stony Brook Stony BrookNY11794 United States Network Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing100864 China Department of Computing Hong Kong Polytechnic University Hong Kong Hong Kong

The inference of traffic volume of the whole network from partial traffic measurements becomes increasingly critical for various network engineering tasks, such as capacity planning and anomaly detection. Previous studies indicate that the matrix completion is a possible solution for this problem. However, as a 2-D matrix cannot sufficiently capture the spatial-temporal features of traffic data, these approaches fail to work when the data missing ratio is high. To fully exploit hidden spatial-temporal structures of the traffic data, this paper models the traffic data as a 3-way traffic tensor and formulates the traffic data recovery problem as a low-rank tensor completion problem. However, the high computation complexity incurred by the conventional tensor completion algorithms prevents its practical application for the traffic data recovery. To reduce the computation cost, we propose a novel sequential tensor completion algorithm, which can efficiently exploit the tensor decomposition result based on the previous traffic data to derive the tensor decomposition upon arriving of new data. Furthermore, to better capture the changes of data correlation over time, we propose a dynamic sequential tensor completion algorithm. To the best of our knowledge, we are the first to propose sequential tensor completion algorithms to significantly speed up the traffic data recovery process. This facilitates the modeling of Internet traffic with the tensor to well exploit the hidden structures of traffic data for more accurate missing data inference. We have done extensive simulations with the real traffic trace as the input. The simulation results demonstrate that our algorithms can achieve significantly better performance compared with the literature tensor and matrix completion algorithms even when the data missing ratio is high. © 1993-2012 IEEE.

关键词： Tensors

Manifold alignment via corresponding projections

学校读者我要写书评

暂无评论

Manifold alignment via corresponding projections

2010 21st British Machine Vision Conference, BMVC 2010

作者： Zhai, Deming Li, Bo Chang, Hong Shan, Shiguang Chen, Xilin Gao, Wen School of Computer Science and Technology Harbin Institute of Technology China Digital Media Research Center Institute of Computing Technology CAS China Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences China Institute of Digital Media Peking University China

ISBN: (纸本)1901725405

In this paper, we propose a novel manifold alignment method by learning the underlying common manifold with supervision of corresponding data pairs from different observation sets. Different from the previous algorithms of semi-supervised manifold alignment, our method learns the explicit corresponding projections from each original observation space to the common embedding space everywhere. Benefiting from this property, our method could process new test data directly rather than re-alignment. Furthermore, our approach doesn't have any assumption on the data structures, thus it could handle more complex cases and get better results compared with previous work. In the proposed algorithm, manifold alignment is formulated as a minimization problem with proper constraints, which could be solved in an analytical manner with closed-form solution. Experimental results on pose manifold alignment of different objects and faces demonstrate the effectiveness of our proposed method. © 2010. The copyright of this document resides with its authors.

关键词：

Modeling topical relevance for multi-turn dialogue generation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Hainan Lan, Yanyan Pang, Liang Chen, Hongshen Ding, Zhuoye Yin, Dawei CAS Key Lab of Network Data Science and Technology Institute of Computing Technology CAS China *** Beijing China University of Chinese Academy of Sciences China

Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly. However, existing models usually use word or sentence level similarities to detect the relevant contexts, which fail to well capture the topical level relevance. In this paper, we propose a new model, named STAR-BTM, to tackle this problem. Firstly, the Biterm Topic Model is pre-trained on the whole training dataset. Then, the topic level attention weights are computed based on the topic representation of each context. Finally, the attention weights and the topic distribution are utilized in the decoding process to generate the corresponding responses. Experimental results on both Chinese customer services data and English Ubuntu dialogue data show that STAR-BTM significantly outperforms several state-of-the-art methods, in terms of both metric-based and human evaluations. Copyright © 2020, The Authors. All rights reserved.

关键词： Stars

Blind separation of noncooperative paired carrier multiple access signals based on improved quantum-inspired evolutionary algorithm and receding horizon optimization

学校读者我要写书评

暂无评论

Blind separation of noncooperative paired carrier multiple a...

作者： Deng, Qi Zhang, Shanshan Chen, Gang Lu, Huaxiang Lab of Artificial Networks Institute of Semiconductors CAS Beijing China University of Chinese Academy of Sciences Beijing China CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China

The single-channel blind source separation of paired carrier multiple access (PCMA) signal is a key technology in satellite communications. Due to the high-order complexity of existing separation methods and the uncertainty of channel parameters, the processing of noncooperative PCMA signals with long memory remains a great challenge. In this article, the blind separation was solved as the joint channel estimation and sequence detection, and a novel blind separation algorithm based on the improved quantum-inspired evolutionary algorithm (IQEA) and receding horizon optimization was proposed. Considering the practical scenarios, a mixed PCMA signal model with noninteger period sampling was presented in advance. Combined with the proposed signal model, the IQEA was applied to recover the uplink signals from the mixed PCMA signals by its iterative estimation. Meanwhile, to reduce the computational complexity caused by long memory of PCMA signals, the receding horizon optimization was introduced to process the whole signal sequence as a dynamic programming problem. The simulation results verified that the proposed RH-IQEA outperforms existing state-of-the-art separation algorithms in the blind separation of noncooperative PCMA signals, with higher accuracy, lower-order complexity and stronger robustness to parameter estimation errors. © 2021 John Wiley & Sons, Ltd.

关键词： Iterative methods

Text Matching application for integration between industry and education 14

学校读者我要写书评

暂无评论

Text Matching application for integration between industry a...

14th International Conference on Measuring technology and Mechatronics Automation, ICMTMA 2022

作者： Luo, Yuxuan Li, Xiaoge School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9781665499781

A new talent training mode of collaboration between industry and education was proposed, which aims to reduce the gaps of talent definition between enterprise demand and college education. We formulates scenario as a text matching task of similarity between courses details and job position information, developed a ERNIE+DPCNN based model for the task. The model has been benchmarked on LCQMC dataset, the results show that it achieves the art-of state performance of Acc 0.8809, Recall 0.8745, and FX score 0.8739, We conducted many experiments about the text similarity calculation between domains of industry and educations. The experiment results show our approach has much potential to optimize the curriculum system while applying in this field. © 2022 IEEE

关键词： Industries Training Mechatronics Automation Collaboration Benchmark testing Task analysis

Iterative Utility Judgment Framework via LLMs Inspired by Relevance in Philosophy

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Hengran Bi, Keping Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China

Utility and topical relevance are critical measures in information retrieval (IR), reflecting system and user perspectives, respectively. While topical relevance has long been emphasized, utility is a higher standard of relevance and is more useful for facilitating downstream tasks, e.g., in Retrieval-Augmented Generation (RAG). When we incorporate utility judgments into RAG, we realize that the topical relevance, utility, and answering in RAG are closely related to the three types of relevance that Schutz discussed from a philosophical perspective. They are topical relevance, interpretational relevance, and motivational relevance, respectively. Inspired by the dynamic iterations of the three types of relevance, we propose an Iterative utiliTy judgmEnt fraMework (ITEM) to promote each step of the cycle of RAG. We conducted extensive experiments on multigrade passage retrieval and factoid questionanswering datasets (i.e., TREC DL, WebAP, and NQ). Experimental results demonstrate significant improvements in utility judgments, ranking of topical relevance, and answer generation upon representative baselines, including multiple single-shot utility judging approaches. Our code and benchmark can be found at https://anonymous.4open. science/r/ITEM-B486/. Copyright © 2024, The Authors. All rights reserved.

关键词： Search engines

Graph convolutional networks using heat kernel for semi-supervised learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xu, Bingbing Shen, Huawei Cao, Qi Cen, Keting Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Graph convolutional networks gain remarkable success in semi-supervised learning on graph-structured data. The key to graph-based semi-supervised learning is capturing the smoothness of labels or features over nodes exerted by graph structure. Previous methods, spectral methods and spatial methods, devote to defining graph convolution as a weighted average over neighboring nodes, and then learn graph convolution kernels to leverage the smoothness to improve the performance of graph-based semi-supervised learning. One open challenge is how to determine appropriate neighborhood that reflects relevant information of smoothness manifested in graph structure. In this paper, we propose GraphHeat, leveraging heat kernel to enhance low-frequency filters and enforce smoothness in the signal variation on the graph. GraphHeat leverages the local structure of target node under heat diffusion to determine its neighboring nodes flexibly, without the constraint of order suffered by previous methods. GraphHeat achieves state-of-the-art results in the task of graph-based semi-supervised classification across three benchmark datasets: Cora, Citeseer and Pubmed. Copyright © 2020, The Authors. All rights reserved.

关键词： Graphic methods