检索结果-内蒙古大学图书馆

CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding

学校读者我要写书评

暂无评论

CroPrompt: Cross-task Interactive Prompting for Zero-shot Sp...

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

作者： Qin, Libo Wei, Fuxuan Chen, Qiguang Zhou, Jingxuan Huang, Shijue Si, Jiasheng Lu, Wenpeng Che, Wanxiang School of Computer Science and Engineering Central South University China Key Laboratory of Data Intelligence and Advanced Computing in Provincial Universities Soochow University China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Harbin Institute of Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences China

ISBN: (纸本)9798350368741

Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU. Additionally, we further introduce a multi-task self-consistency mechanism to mitigate the error propagation caused by the intent information injection. We conduct extensive experiments on the standard SLU benchmark and the results reveal that CroPrompt consistently outperforms the existing prompting approaches. In addition, the multi-task self-consistency mechanism can effectively ease the error propagation issue, thereby enhancing the performance. We hope this work can inspire more research on cross-task prompting for SLU. © 2025 IEEE.

关键词：

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

Disentangled Noisy Correspondence Learning

学校读者我要写书评

暂无评论

IEEE Transactions on Image Processing 2025年 34卷 2602-2615页

作者： Dang, Zhuohang Luo, Minnan Wang, Jihong Jia, Chengyou Han, Haochen Wan, Herun Dai, Guang Chang, Xiaojun Wang, Jingdong Xi’an Jiaotong University School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi’an710049 China SGIT AI Laboratory Xi’an710048 China State Grid Corporation of China State Grid Shaanxi Electric Power Company Ltd. Xi’an710048 China University of Science and Technology of China School of Information Science and Technology Hefei230026 China Abu Dhabi United Arab Emirates Baidu Inc. Beijing100085 China

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of modality-invariant information (MII) and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal inputs for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL’s efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. © 1992-2012 IEEE.

关键词： information theory

Effective Instruction Parsing Plugin for Complex Logical Query Answering on knowledge Graphs 34

学校读者我要写书评

暂无评论

Effective Instruction Parsing Plugin for Complex Logical Que...

34th ACM Web Conference, WWW 2025

作者： Zhuo, Xingrui Wang, Jiapu Wu, Gongqing Pan, Shirui Wu, Xindong Hefei University of Technology Anhui Hefei China Beijing University of Technology Beijing China Griffith University Gold Coast QLD Australia The Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) School of Computer Science and Information Engineering Hefei University of Technology China

ISBN: (纸本)9798400712746

knowledge Graph Query Embedding (KGQE) aims to embed First-Order Logic (FOL) queries in a low-dimensional KG space for complex reasoning over incomplete KGs. To enhance the generalization of KGQE models, recent studies integrate various external information (such as entity types and relation context) to better capture the logical semantics of FOL queries. The whole process is commonly referred to as Query Pattern Learning (QPL). However, current QPL methods typically suffer from the pattern-entity alignment bias problem, leading to the learned defective query patterns limiting KGQE models’ performance. To address this problem, we propose an effective Query Instruction Parsing Plugin (QIPP) that leverages the context awareness of Pre-trained Language Models (PLMs) to capture latent query patterns from code-like query instructions. Unlike the external information introduced by previous QPL methods, we first propose code-like instructions to express FOL queries in an alternative format. This format utilizes textual variables and nested tuples to convey the logical semantics within FOL queries, serving as raw materials for a PLM-based instruction encoder to obtain complete query patterns. Building on this, we design a query-guided instruction decoder to adapt query patterns to KGQE models. To further enhance QIPP’s effectiveness across various KGQE models, we propose a query pattern injection mechanism based on compressed optimization boundaries and an adaptive normalization component, allowing KGQE models to utilize query patterns more efficiently. Extensive experiments demonstrate that our plug- and-play method¹ improves the performance of eight basic KGQE models and outperforms two state-of-the-art QPL methods. © 2025 Copyright held by the owner/author(s).

关键词： Complex Query Answering knowledge Graph Pre-trained Language Model Query Pattern Learning

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

Joint Double Auction-Based Channel Selection in Wireless Monitoring Networks

学校读者我要写书评

暂无评论

IEEE Transactions on Network and Service Management 2025年

作者： Xia, Na Chen, Lei Li, Meng Yin, Yutao Zhang, Ke Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data China State Grid Electric Power Research Institute Co. Ltd Hefei230088 China

In wireless networks, utilizing sniffers for fault analysis, traffic traceback, and resource optimization is a crucial task. However, existing centralized algorithms cannot be applied to high-density wireless networks. Therefore, distributed optimization of channel selection to maximize the monitoring rate of sensors in Wireless Monitoring Networks (WMNs) is a challenge. This paper proposes a joint double auction-based distributed channel selection algorithm (J2A-CS) to maximize overall quality of monitoring (QoM). First, sniffers are redundantly deployed in WMNs, and an initial channel allocation strategy is formulated. Subsequently, sniffers collectively act as buyers and sellers at different stages. Finally, buyers bid asynchronously, and sellers settle synchronously to maximize the seller's marginal revenue and update the channel selection scheme. As a distributed channel selection algorithm, J2A-CS addresses the highest overall QoM issue in WMNs, demonstrating high scalability and fault tolerance. Simulation results show that J2A-CS significantly improves QoM compared to existing distributed algorithms and outperforms centralized algorithms in high-density scenarios. © 2004-2012 IEEE.

关键词： Sales

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

Offline Reinforcement Learning via Conservative Smoothing and Dynamics Controlling

学校读者我要写书评

暂无评论

Offline Reinforcement Learning via Conservative Smoothing an...

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

作者： Haihong Guo Fengxin Li Jiao Li Hongyan Liu School of Information Renmin University of China China Chinese Academy of Medical Sciences / Peking Union Medical College Institute of Medical Information / Medical Library China Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education China School of Economics and Management Tsinghua University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Offline Reinforcement Learning (RL) optimizes policy using pre-collected data instead of direct environment interaction, offering a safe and cost-effective solution for sequential decision-making in the real world. However, it faces challenges such as distribution shift issues and vulnerability under perturbations. Researchers have developed various conservative methods to improve the robustness of offline RL. Nevertheless, model-based methods can result in transition distribution shift issues, while model-free value-based uncertainty penalty methods may not be sufficiently robust. To address these problems, we propose a new method called Robust Offline RL via Conservative Smoothing and Dynamics Controlling (RCSD). To achieve reliable value estimation of out-of-distribution (OOD) actions, RCSD uses both model-free uncertainty penalty and model-based simulation methods. It introduces a new one-step simulation method with conservative dynamics controlling to avoid value overestimation caused by transition distribution shifts. Moreover, RCSD considers both current and next states when generating OOD states to ensure cautious value estimation and efficient data utilization. RCSD uses conservative Q-smoothing and policy smoothing to strengthen the policy against sudden changes under perturbations. Experiments on D4RL benchmark demonstrate that RCSD can achieve state-of-the-art performance compared to baselines in either benchmark or adversarial attack tests.

关键词： Uncertainty Smoothing methods Perturbation methods Estimation Reinforcement learning Benchmark testing Signal processing Robustness Speech processing Faces