检索结果-内蒙古大学图书馆

A Query Optimization Method Utilizing Large Language Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yao, Zhiming Li, Haoyang Zhang, Jing Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE China Engineering Research Center of Database and Business Intelligence MOE China

Query optimization is a critical task in database systems, focused on determining the most efficient way to execute a query from an enormous set of possible strategies. Traditional approaches rely on heuristic search methods and cost predictions, but these often struggle with the complexity of the search space and inaccuracies in performance estimation, leading to suboptimal plan choices. This paper presents LLMOpt, a novel framework that leverages Large Language Models (LLMs) to address these challenges through two innovative components: (1) LLM for Plan Candidate Generation (LLMOpt(G)), which eliminates heuristic search by utilizing the reasoning abilities of LLMs to directly generate high-quality query plans, and (2) LLM for Plan Candidate Selection (LLMOpt(S)), a list-wise cost model that compares candidates globally to enhance selection accuracy. To adapt LLMs for query optimization, we propose fine-tuning pre-trained models using optimization data collected offline. Experimental results on the JOB, JOB-EXT, and Stack benchmarks show that LLMOpt(G) and LLMOpt(S) outperform state-of-the-art methods, including PostgreSQL, BAO, and HybridQO. Notably, LLMOpt(S) achieves the best practical performance, striking a balance between plan quality and inference efficiency. Copyright © 2025, The Authors. All rights reserved.

关键词： Structured Query Language

LLMIdxAdvis: Resource-Efficient Index Advisor Utilizing Large Language Model

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhao, Xinxin Li, Haoyang Zhang, Jing Huang, Xinmei Zhang, Tieying Chen, Jianjun Shi, Rui Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE China Engineering Research Center of Database and Business Intelligence MOE China ByteDance China

Index recommendation is essential for improving query performance in database management systems (DBMSs) through creating an optimal set of indexes under specific constraints. Traditional methods, such as heuristic and learning-based approaches, are effective but face challenges like lengthy recommendation time, resource-intensive training, and poor generalization across different workloads and database schemas. To address these issues, we propose LLMIdxAdvis, a resource-efficient index advisor that uses large language models (LLMs) without extensive fine-tuning. LLMIdxAdvis frames index recommendation as a sequence-to-sequence task, taking target workload, storage constraint, and corresponding database environment as input, and directly outputting recommended indexes. It constructs a high-quality demonstration pool offline, using GPT-4-Turbo to synthesize diverse SQL queries and applying integrated heuristic methods to collect both default and refined labels. During recommendation, these demonstrations are ranked to inject database expertise via in-context learning. Additionally, LLMIdxAdvis extracts workload features involving specific column statistical information to strengthen LLM’s understanding, and introduces a novel inference scaling strategy combining vertical scaling (via "Index-Guided Major Voting" and Best-of-N) and horizontal scaling (through iterative "self-optimization" with database feedback) to enhance reliability. Experiments on 3 OLAP and 2 real-world benchmarks reveal that LLMIdxAdvis delivers competitive index recommendation with reduced runtime, and generalizes effectively across different workloads and database schemas. Copyright © 2025, The Authors. All rights reserved.

关键词： Query languages

OmniSQL: Synthesizing High-quality Text-to-SQL data at Scale

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Haoyang Wu, Shang Zhang, Xiaokang Huang, Xinmei Zhang, Jing Jiang, Fuxin Wang, Shuai Zhang, Tieying Chen, Jianjun Shi, Rui Chen, Hong Li, Cuiping Engineering Research Center of Database and Business Intelligence MOE China School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE China ByteDance Inc China

Text-to-SQL, the task of translating natural language questions into SQL queries, plays a crucial role in enabling non-experts to interact with databases. While recent advancements in large language models (LLMs) have significantly enhanced text-to-SQL performance, existing approaches face notable limitations in real-world text-to-SQL applications. Prompting-based methods often depend on closed-source LLMs, which are expensive, raise privacy concerns, and lack customization. Fine-tuning-based methods, on the other hand, suffer from poor generalizability due to the limited coverage of publicly available training data. To overcome these challenges, we propose a novel and scalable text-to-SQL data synthesis framework for automatically synthesizing large-scale, high-quality, and diverse datasets without extensive human intervention. Using this framework, we introduce SynSQL-2.5M, the first million-scale text-to-SQL dataset, containing 2.5 million samples spanning over 16,000 synthetic databases. Each sample includes a database, SQL query, natural language question, and chain-of-thought (CoT) solution. Leveraging SynSQL-2.5M, we develop OmniSQL, a powerful open-source text-to-SQL model available in three sizes: 7B, 14B, and 32B. Extensive evaluations across nine datasets demonstrate that OmniSQL achieves state-of-the-art performance, matching or surpassing leading closed-source and open-source LLMs, including GPT-4o and DeepSeek-V3, despite its smaller size. We release all code, datasets, and models to support further research. Copyright © 2025, The Authors. All rights reserved.

关键词： Structured Query Language

LoRS: Efficient Low-Rank Adaptation for Sparse Large Language Model

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hu, Yuxuan Zhang, Jing Chen, Xiaodong Zhao, Zhe Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China Engineering Research Center of Database and Business Intelligence Beijing China Tencent AI Lab Beijing China

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with additional masking mechanisms. Despite these successes, such approaches suffer from an increased memory and computation overhead, which affects efficiency of LoRA methods. In response to this limitation, we introduce LoRS, an innovative method designed to achieve both memory and computation efficiency when fine-tuning sparse LLMs. To mitigate the substantial memory and computation demands associated with preserving sparsity, our approach incorporates strategies of weight recompute and computational graph rearrangement. In addition, we also improve the effectiveness of LoRS through better adapter initialization. These innovations lead to a notable reduction in memory and computation consumption during the fine-tuning phase, all while achieving performance levels that outperform existing LoRA approaches. © 2025, CC BY.

关键词： Problem oriented languages

SoAy: A Solution-based LLM API-using Methodology for Academic Information Seeking 25

学校读者我要写书评

暂无评论

SoAy: A Solution-based LLM API-using Methodology for Academi...

Proceedings of the 31st ACM SIGKDD Conference on knowledge Discovery and data Mining V.1

作者： Yuanchun Wang Jifan Yu Zijun Yao Jing Zhang Yuyang Xie Shangqing Tu Yiyang Fu Youhe Feng Jinkai Zhang Jingyao Zhang Bowen Huang Yuanyao Li Huihui Yuan Lei Hou Juanzi Li Jie Tang School of Information Renmin University of China Beijing China & Key Laboratory of Data Engineering and Knowledge Engineering MOE Beijing China Institute of Education Tsinghua University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China School of Information Renmin University of China Beijing China & Engineering Research Center of Database and Business Intelligence MOE Beijing China School of Information Renmin University of China Beijing China Zhipu AI Beijing China

ISBN: (纸本)9798400712456

Applying large language models (LLMs) to academic API usage shows promise in reducing researchers' efforts to seek academic information. However, current LLM methods for using APIs struggle with the complex API coupling commonly encountered in academic queries. To address this, we introduce SoAy, a solution-based LLM methodology for academic information seeking. SoAy enables LLMs to generate code for invoking APIs, guided by a pre-constructed API calling sequence referred to as a solution. This solution simplifies the model's understanding of complex API relationships, while the generated code enhances reasoning efficiency. LLMs are aligned with this solution-oriented, code-based reasoning method by automatically enumerating valid API coupling sequences and transforming them into queries and executable *** evaluate SoAy, we introduce SoAyBench, an evaluation benchmark accompanied by SoAyEval, built upon a cloned environment of APIs from AMiner. Experimental results demonstrate a 34.58-75.99% performance improvement compared to state-of-the-art LLM API-based baselines. All datasets, codes, tuned models, and deployed online services are publicly accessible at https://***/RUCKBReasoning/SoAy.

关键词： academic information seeking

database Research： Achievements and Challenges

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2006年第5期21卷 823-837页

作者：王珊杜小勇孟小峰陈红 School of Information Renmin University of China MOE Key Lab of Data Engineering and Knowledge Engineering Beijing 100872 P.R. China

database system is the infrastructure of the modern information system. The R＆D in the database system and its technologies is one of the important research topics in the field. The database R＆D in China took off later but it moves along by giant steps. This report presents the achievements Renmin University of China （RUC） has made in the past 25 years and at the same time addresses some of the research projects we, RUC, are currently working on. The National Natural Science Foundation of China supports and initiates most of our research projects and these successfully conducted projects have produced fruitful results.

关键词： database management system parallel database systems Chinese database systems self-managing databases P2P computing and databases data warehousing OLAP Web data management XML mobile data management semantic web contextual information retrieval

An effective scheme for top-k frequent itemset mining under differential privacy conditions

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第5期63卷 200-202页

作者： Wenjuan LIANG Hong CHEN Jing ZHANG Dan ZHAO Cuiping LI Key Lab of Data Engineering and Knowledge Engineering of MOE Renmin University of China College of Computer and Information Engineering Henan University

Dear editor,Frequent itemset mining (FIM) is important in many data mining applications [1], such as web log mining and trend analysis. However, if the data are sensitive (e.g., web browsing history), directly releasing frequent itemsets and their support may breach user privacy. The protection of user privacy while obtaining statistical information is im-

关键词： An effective scheme for top-k frequent itemset mining under differential privacy conditions

Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching for Speaker Diarization

学校读者我要写书评

暂无评论

Flow-TSVAD: Target-Speaker Voice Activity Detection via Late...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhengyang Chen Bing Han Shuai Wang Yidi Jiang Yanmin Qian Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China National University of Singapore Singapore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Speaker diarization is typically considered as a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore for the first time the use of neural network-based generative methods for speaker diarization. We implement a Flow-Matching (FM) based generative algorithm within the sequenceto-sequence target speaker voice activity detection (Seq2Seq-TSVAD) diarization system. Our experiments reveal that applying the generative method directly to the original binary label sequence space of the TS-VAD output is ineffective. To address this issue, we propose mapping the binary label sequence into a dense latent space before applying the generative algorithm, and our proposed Flow-TSVAD method can significantly outperform the traditional Seq2Seq-TSVAD system. Additionally, we observe that the FM algorithm converges rapidly during the inference stage, only requiring two inference steps to achieve promising results. Moreover, as a generative model, Flow-TSVAD allows for sampling different diarization results by running the model multiple times, so the ensemble system combining the results from various sampling instances can further boost the diarization performance.

关键词： Voice activity detection Frequency modulation Computational modeling Signal processing algorithms Signal processing Inference algorithms Acoustics Computational efficiency

MRST-- An Efficient Monitoring Technology of Summarization on Stream data

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2007年第2期22卷 190-196页

作者：樊小泊解婷婷李翠平陈红 School of Information Renmin University of China Beijing 100872 China Key Laboratory of Data Engineering and Knowledge Engineering MOE Beijing 100872 China

Monitoring on data streams is an efficient method of acquiring the characters of data stream. However the available resources for each data stream are limited, so the problem of how to use the limited resources to process infinite data stream is an open challenging problem. In this paper, we adopt the wavelet and sliding window methods to design a multi-resolution summarization data structure, the Multi-Resolution Summarization Tree （MRST） which can be updated incrementally with the incoming data and can support point queries, range queries, multi-point queries and keep the precision of queries. We use both synthetic data and real-world data to evaluate our algorithm. The results of experiment indicate that the efficiency of query and the adaptability of MRST have exceeded the current algorithm, at the same time the realization of it is simpler than others.

关键词： Haar wavelet sliding window stream data