检索结果-内蒙古大学图书馆

Dual-Aspect Noise-Based Regularization for Multi-Modal Relation Extraction in Media Posts

学校读者我要写书评

暂无评论

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 1324-1336页

作者： Kai Sun Bin Shi Samuel Mensah Wenjian Liu Bo Dong School of Computer Science and Technology and Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an China School of Computer Science and Technology The University of Sheffield Sheffield U.K. Faculty of Data Science City University of Macau Macau China School of Continuing Education and Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an China

Multi-Modal Relation Extraction (MMRE) plays a key role in various multimedia applications including, recommendation and information retrieval systems. MMRE aims to extract the semantic relation between entities by leveraging context from a text-image pair. By utilizing context from images, the challenge of learning from noisy images in MMRE emerges as a research problem by itself. For instance, subtle variations in similar images can act as noise and potentially impact the predictions made by MMRE models. To tackle this problem, current work utilizes attention mechanisms to fuse relevant text and image features or devise data augmentation techniques (e.g., via generative models) to improve generalization. However, the current performance still remains unsatisfactory. In an effort to improve upon the performance, we propose a Dual-Aspect Noise-based Regularization framework that encompasses two techniques: 1) noise removal through an adaptive gating mechanism, 2) fighting noise with noise to improve feature stability in the learning process. We find that combining these techniques encourages the model to focus on more relevant image features for MMRE. We carry out extensive experiments and demonstrate that our proposed model is further enhanced by exploring data augmentation techniques. This additional improvement leads the model to achieve state-of-the-art performance on the widely-used Multi-modal Neural Relation Extraction (MNRE) dataset, and show its effectiveness and generalizability on the Multi-Modal Named Entity Recognition task.

关键词： Feature extraction Noise data mining Noise measurement Social networking (online) Adaptation models Transformers Training Predictive models data models

CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Bohan Zhang, Xiaokang Zhang, Jing Yu, Jifan Luo, Sijia Tang, Jie School of Information Renmin University of China China Tsinghua University China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China

Current inference scaling methods, such as Self-consistency and Best-of-N, have proven effective in improving the accuracy of LLMs on complex reasoning tasks. However, these methods rely heavily on the quality of candidate responses and are unable to produce correct answers when all candidates are incorrect. In this paper, we propose a novel inference scaling strategy, CoT-based Synthesizer, which leverages CoT reasoning to synthesize superior answers by analyzing complementary information from multiple candidate responses, even when all candidate responses are flawed. To enable a lightweight and cost-effective implementation, we introduce an automated data generation pipeline that creates diverse training data. This allows smaller LLMs trained on this data to improve the inference accuracy of larger models, including API-based LLMs. Experimental results across four benchmark datasets with seven policy models demonstrate that our method significantly enhances performance, with gains of 11.8% for Llama3-8B and 10.3% for GPT-4o on the MATH dataset. The corresponding training data and code are publicly available on the repository. Copyright © 2025, The Authors. All rights reserved.

关键词： data accuracy

Dynamic Scaling of Unit Tests for Code Reward Modeling

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ma, Zeyao Zhang, Xiaokang Zhang, Jing Yu, Jifan Luo, Sijia Tang, Jie School of Information Renmin University of China China Tsinghua University China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China

Current large language models (LLMs) often struggle to produce accurate solutions on the first attempt for code generation. Prior research tackles this challenge by generating multiple candidate solutions and validating them with LLM-generated unit tests. The execution results of unit tests serve as reward signals to identify correct solutions. As LLMs always confidently make mistakes, these unit tests are not reliable, thereby diminishing the quality of reward signals. Motivated by the observation that scaling the number of solutions improves LLM performance, we explore the impact of scaling unit tests to enhance reward signal quality. Our pioneer experiment reveals a positive correlation between the number of unit tests and reward signal quality, with greater benefits observed in more challenging problems. Based on these insights, we propose CodeRM-8B, a lightweight yet effective unit test generator that enables efficient and high-quality unit test scaling. Additionally, we implement a dynamic scaling mechanism that adapts the number of unit tests based on problem difficulty, further improving efficiency. Experimental results show that our approach significantly improves performance across various models on three benchmarks (e.g., with gains of 18.43% for Llama3-8B and 3.42% for GPT-4o-mini on HumanEval Plus). © 2025, CC BY-SA.

关键词：

A Part-of-Speech Tagging Model Employing Word Clustering and Syntactic Parsing

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2025年第1期23卷 109-114页

作者： Lichi Yuan School of Information Technology Jiangxi University of Finance and Economics Nanchang China Jiangxi Key Laboratory of Data and Knowledge Engineering Jiangxi University of Finance and Economics Nanchang China

Part-Of-Speech tagging is a basic task in the field of natural language processing. This paper builds a POS tagger based on improved Hidden Markov model, by employing word clustering and syntactic parsing model. Firstly, In order to overcome the defects of the classical HMM, Markov family model (MFM), a new statistical model was introduced. Secondly, to solve the problem of data sparseness, we propose a bottom-to-up hierarchical word clustering algorithm. Then we combine syntactic parsing with part-of-speech tagging. The Part-of-Speech tagging experiments show that the improved Part-Of-Speech tagging model has higher performance than Hidden Markov models (HMMs) under the same testing conditions, the precision is enhanced from 94.642% to 97.235%.

关键词：

Enhancing Continuous Cognitive Diagnosis with Fuzzy Strategy-Based Hybrid Genetic Algorithm 3rd

学校读者我要写书评

暂无评论

Enhancing Continuous Cognitive Diagnosis with Fuzzy Strateg...

3rd International Conference on Cyberspace Simulation and Evaluation, CSE 2024

作者： He, Chenlong Hu, Xuegang Cao, Zhiyong Bu, Chenyang Luo, Wenjian Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education Hefei China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and Technology Harbin Institute of Technology Harbin China

ISBN: (纸本)9789819645053

Continuous cognitive diagnosis models (CDMs) are vital tools for assessing students’ mastery of knowledge points. However, traditional probability-based CDMs are prone to falling into local optima due to their use of single-point search methods, which can affect the accuracy of the models. To address this issue, we propose a hybrid genetic algorithm (HGA) enhanced with a fuzzy strategy to improve continuous cognitive diagnosis. This approach introduces the multidimensional item response theory (MIRT) as a local search operator to boost diagnostic precision. Additionally, considering the limitation on the number of local searches within a finite time, we introduce a fuzzy strategy that dynamically adjusts the number of local searches by evaluating the similarity between the current population and the elite set, thus balancing global and local search. Experimental results on three real-world datasets demonstrate that our method significantly outperforms six existing comparison models, validating the effectiveness of the fuzzy strategy and continuous CDM. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Continuous cognitive diagnosis Educational data mining Evolutionary algorithm Local search

How to Mitigate Information Loss in knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Manzong Bu, Chenyang He, Yi Wu, Xindong Key Laboratory of Knowledge Engineering with Big Data [Hefei University of Technology Ministry of Education China School of Data Science William & Mary WilliamsburgVA United States

knowledge Graph (KG)-augmented Large Language Models (LLMs) have recently propelled significant advances in complex reasoning tasks, thanks to their broad domain knowledge and contextual awareness. Unfortunately, current methods often assume KGs to be complete, which is impractical given the inherent limitations of KG construction and the potential loss of contextual cues when converting unstructured text into entity-relation triples. In response, this paper proposes the Triple Context Restoration and Query-driven Feedback (TCR-QF) framework, which reconstructs the textual context underlying each triple to mitigate information loss, while dynamically refining the KG structure by iteratively incorporating query-relevant missing knowledge. Experiments on five benchmark question-answering datasets substantiate the effectiveness of TCR-QF in KG and LLM integration, where it achieves a 29.1% improvement in Exact Match and a 15.5% improvement in F1 over its state-of-the-art GraphRAG competitors. © 2025, CC BY.

关键词： knowledge graph

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

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