检索结果-内蒙古大学图书馆

Large Language Model-Based Event Relation Extraction with Rationales 31

学校读者我要写书评

暂无评论

Large Language Model-Based Event Relation Extraction with Ra...

31st International Conference on Computational Linguistics, COLING 2025

作者： Hu, Zhilei Li, Zixuan Jin, Xiaolong Bai, Long Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of SciencesSchool of Computer Science and Technology University of Chinese Academy of Sciences

ISBN: (纸本)9798891761964

Event Relation Extraction (ERE) aims to extract various types of relations between different events within texts. Although Large Language Models (LLMs) have demonstrated impressive capabilities in many natural language processing tasks, existing ERE methods based on LLMs still face three key challenges: (1) Time Inefficiency: The existing pairwise method of combining events and determining their relations is time-consuming for LLMs. (2) Low Coverage: When dealing with numerous events in a document, the limited generation length of fine-tuned LLMs restricts the coverage of their extraction results. (3) Lack of Rationale: Essential rationales concerning the results that could enhance the reasoning ability of the model are overlooked. To address these challenges, we propose LLMERE, an LLM-based approach with rationales for the ERE task. LLMERE transforms ERE into a question-and-answer task that may have multiple answers. By extracting all events related to a specified event at once, LLMERE reduces time complexity from O(n2) to O(n), compared to the pairwise method. Subsequently, LLMERE enhances the coverage of extraction results by employing a partitioning strategy that highlights only a portion of the events in the document at a time. In addition to the extracted results, LLMERE is also required to generate corresponding rationales/reasons behind them, in terms of event coreference information or transitive chains of event relations. Experimental results on three widely used datasets show that LLMERE achieves significant improvements over baseline methods. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

SmartZone: Runtime Support for Secure and Efficient On-device Inference on ARM TrustZone

学校读者我要写书评

暂无评论

IEEE Transactions on Computers 2025年第6期74卷 2144-2158页

作者： Jian, Zhaolong Liu, Xu Dong, Qiankun Cheng, Longkai Xie, Xueshuo Li, Tao Nankai University College of Computer Science Tianjin China Tianjin Key Laboratory of Network Tianjin China Data Science Technology Tianjin China Haihe Lab of ITAI Tianjin China

On-device inference is a burgeoning paradigm that performs model inference locally on end devices, allowing private data to remain local. ARM TrustZone as a widely supported trusted execution environment has been applied to provide confidentiality protection for on-device inference. However, with the rise of large-scale models like large language models (LLMs), TrustZone-based on-device inference faces challenges in migration difficulties and inefficient execution. The rudimentary TEE OS on TrustZone lacks both the inference runtime needed for building models and the parallel support necessary to accelerate inference. Moreover, the limited secure memory resources on end devices further constrain the model size and degrade performance. In this paper, we propose SmartZone to provide runtime support for secure and efficient on-device inference on TrustZone. SmartZone consists three main components: (1) a trusted inference-oriented operator set, providing the underlying mechanisms adapted to the TrustZone’s execution mode for trusted inference of DNN models and LLMs. (2) the proactive multi-threading parallel support, which increases the number of CPU cores in the secure state via cross-world thread collaboration to achieve parallelism, and (3) the on-demand secure memory management method, which statically allocates the appropriate secure memory size based on pre-execution resource analysis. We implement a prototype of SmartZone on the Raspberry Pi 3B+ board and evaluate it on four well-known DNN models and llama2 LLM. Extensive experimental results show that SmartZone provides end-to-end protection for on-device inference while maintaining excellent performance. Compared to the origin trusted inference, SmartZone accelerates the inference speed by up to 4.26× and reduces energy consumption by 65.81%. © 1968-2012 IEEE.

关键词： Memory management

MDPO: Customized Direct Preference Optimization with a Metric-based Sampler for Question and Answer Generation 31

学校读者我要写书评

暂无评论

MDPO: Customized Direct Preference Optimization with a Metri...

31st International Conference on Computational Linguistics, COLING 2025

作者： Wang, Yihang Tian, Bowen Su, Yueyang Fan, Yixing Guo, Jiafeng Beijing University of Posts and Telecommunications Beijing China Guangzhou China CAS Key Lab of Network Data Science and Technology ICT CAS Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798891761964

With the extensive use of large language models, automatically generating QA datasets for domain-specific fine-tuning has become crucial. However, considering the multifaceted demands for readability, diversity, and comprehensiveness of QA data, current methodologies fall short in producing high-quality QA datasets. Moreover, the dependence of existing evaluation metrics on ground truth labels further exacerbates the challenges associated with the selection of QA data. In this paper, we introduce a novel method for QA data generation, denoted as MDPO. We proposes a set of unsupervised evaluation metrics for QA data, enabling multidimensional assessment based on the relationships among context,question and answer. Furthermore, leveraging these metrics, we implement a customized direct preference optimization process that guides large language models to produce high-quality and domain-specific QA pairs. Empirical results on public datasets indicate that MDPO's performance substantially surpasses that of state-of-the-art methods. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

NeuVSA: A Unified and Efficient Accelerator for Neural Vector Search 31

学校读者我要写书评

暂无评论

NeuVSA: A Unified and Efficient Accelerator for Neural Vecto...

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

作者： Yuan, Ziming Dai, Lei Li, Wen Zhang, Jie Liang, Shengwen Wang, Ying Liu, Cheng Li, Huawei Li, Xiaowei Guo, Jiafeng Wang, Peng Chen, Renhai Zhang, Gong Shanxi University School of Computer and Information Technology China Peking University School of Computer Science China Institute of Computing Technology CAS State Key Lab of Processors China University of Chinese Academy of Sciences China Zhongguancun National Laboratory Beijing China Institute of Computing Technology CAS Key Lab of Network Data Science and Technology China Huawei Technologies Co. Ltd. China

ISBN: (纸本)9798331506476

Neural Vector Search (NVS) has exhibited superior search quality over traditional key-based strategies for information retrieval tasks. An effective NVS architecture requires high recall, low latency, and high throughput to enhance user experience and cost-efficiency. However, implementing NVS on existing neural network accelerators and vector search accelerators is sub-optimal due to the separation between the embedding stage and vector search stage at both algorithm and architecture levels. Fortunately, we unveil that Product Quantization (PQ) opens up an opportunity to break separation. However, existing PQ algorithms and accelerators still focus on either the embedding stage or the vector search stage, rather than both simultaneously. Simply combining existing solutions still follows the beaten track of separation and suffers from insufficient parallelization, frequent data access conflicts, and the absence of scheduling, thus failing to reach optimal recall, latency, and throughput. To this end, we propose a unified and efficient NVS accelerator dubbed NeuVSA based on algorithm and architecture co-design philosophy. Specifically, on the algorithm level, we propose a learned PQ-based unified NVS algorithm that consolidates two separate stages into the same computing and memory access paradigm. It integrates an end-to-end joint training strategy to learn the optimal codebook and index for enhanced recall and reduced PQ complexity, thus achieving smoother acceleration. On the architecture level, we customize a homogeneous NVS accelerator based on the unified NVS algorithm. Each sub-accelerator is optimized to exploit all parallelism exposed by unified NVS, incorporating a structured index assignment strategy and an elastic on-chip buffer to alleviate buffer conflicts for reduced latency. All sub-accelerators are coordinated using a hardware-aware scheduling strategy for boosted throughput. Experimental results show that the joint training strategy improves recall

关键词： network embeddings

Tailoring Table Retrieval from a Field-aware Hybrid Matching Perspective

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Da Bi, Keping Guo, Jiafeng Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS China University of Chinese Academy of Sciences China

Table retrieval, essential for accessing information through tabular data, is less explored compared to text retrieval. The row/column structure and distinct fields of tables (including titles, headers, and cells) present unique challenges. For example, different table fields have varying matching preferences: cells may favor finer-grained (word/phrase level) matching over broader (sentence/passage level) matching due to their fragmented and detailed nature, unlike titles. This necessitates a table-specific retriever to accommodate the various matching needs of each table field. Therefore, we introduce a Table-tailored HYbrid Matching rEtriever (THYME), which approaches table retrieval from a field-aware hybrid matching perspective. Empirical results on two table retrieval benchmarks, NQ-TABLES and OTT-QA, show that THYME significantly outperforms state-of-the-art baselines. Comprehensive analyses confirm the differing matching preferences across table fields and validate the design of THYME. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ni, Shiyu Bi, Keping Guo, Jiafeng Yu, Lulu Bi, Baolong Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS China University of Chinese Academy of Sciences China

Large language models (LLMs) exhibit impressive performance across diverse tasks but often struggle to accurately gauge their knowledge boundaries, leading to confident yet incorrect responses. This paper explores leveraging LLMs’ internal states to enhance their perception of knowledge boundaries from efficiency and risk perspectives. We investigate whether LLMs can estimate their confidence using internal states before response generation, potentially saving computational resources. Our experiments on datasets like Natural Questions, HotpotQA, and MMLU reveal that LLMs demonstrate significant pre-generation perception, which is further refined post-generation, with perception gaps remaining stable across varying conditions. To mitigate risks in critical domains, we introduce Consistency-based Confidence Calibration (C3), which assesses confidence consistency through question reformulation. C3 significantly improves LLMs’ ability to recognize their knowledge gaps, enhancing the unknown perception rate by 5.6% on NQ and 4.9% on HotpotQA. Our findings suggest that pre-generation confidence estimation can optimize efficiency, while C3 effectively controls output risks, advancing the reliability of LLMs in practical applications © 2025, CC BY.

关键词： Depth perception

Generative Retrieval for Book Search

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tang, Yubao Zhang, Ruqing Guo, Jiafeng de Rijke, Maarten Liu, Shihao Wang, Shuaiqiang Yin, Dawei Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS University of Chinese Academy of Sciences University of Amsterdam Amsterdam Netherlands University of Amsterdam Amsterdam Netherlands CAS Key Lab of Network Data Science and Technology ICT CAS University of Chinese Academy of Sciences Beijing China Baidu Inc Beijing China

In book search, relevant book information should be returned in response to a query. Books contain complex, multi-faceted information such as metadata, outlines, and main text, where the outline provides hierarchical information between chapters and sections. Generative retrieval (GR) is a new retrieval paradigm that consolidates corpus information into a single model to generate identifiers of documents that are relevant to a given query. How can GR be applied to book search? Directly applying GR to book search is a challenge due to the unique characteristics of book search: (i) The model needs to retain the complex, multi-faceted information of the book, which increases the demand for labeled data. (ii) Splitting book information and treating it as a collection of separate segments for learning might result in a loss of hierarchical information. We propose an effective Generative retrieval framework for Book Search (GBS) that features two main components: (i) data augmentation and (ii) outline-oriented book encoding. For data augmentation, GBS constructs multiple query-book pairs for training;it constructs multiple book identifiers based on the outline, various forms of book contents, and simulates real book retrieval scenarios with varied pseudo-queries. This includes coverage-promoting book identifier augmentation, allowing the model to learn to index effectively, and diversity-enhanced query augmentation, allowing the model to learn to retrieve effectively. Outline-oriented book encoding improves length extrapolation through bi-level positional encoding and retentive attention mechanisms to maintain context over long sequences. Experiments on a proprietary Baidu dataset demonstrate that GBS outperforms strong baselines, achieving a 9.8% improvement in terms of MRR@20, over the state-of-the-art RIPOR method. Experiments on public datasets confirm the robustness and generalizability of GBS, highlighting its potential to enhance book retrieval. © 2025, CC BY.

关键词： Encoding (symbols)

Security analysis and secured access design for networks of image remote sensing

学校读者我要写书评

暂无评论

Digital Communications and networks 2025年第1期11卷 136-144页

作者： Juan Zhao Haibo Dai Xiaolong Xu Hao Yan Zheng Zhang Chunguo Li School of Network Security Jinling Institute of TechnologyNanjing 211169China School of IoT Nanjing University of Posts and Telecommunications(NJUPT)Nanjing 210003China Jiangsu Key Lab.of Big Data Security and Intelligent Processing NJUPTNanJing 210003China School of Information Science and Engineering Southeast UniversityNanjing 210096China

The secured access is studied in this paper for the network of the image remote *** sensor in this network encounters the information security when uploading information of the images wirelessly from the sensor to the central collection *** order to enhance the sensing quality for the remote uploading,the passive reflection surface technique is *** one eavesdropper that exists nearby this sensor is keeping on accessing the same networks,he may receive the same image from this *** goal in this paper is to improve the SNR of legitimate collection unit while cut down the SNR of the eavesdropper as much as possible by adaptively adjust the uploading power from this sensor to enhance the security of the remote sensing *** order to achieve this goal,the secured energy efficiency performance is theoretically analyzed with respect to the number of the passive reflection elements by calculating the instantaneous performance over the channel fading *** on this theoretical result,the secured access is formulated as a mathematical optimization problem by adjusting the sensor uploading power as the unknown variables with the objective of the energy efficiency maximization while satisfying any required maximum data rate of the eavesdropper ***,the analytical expression is theoretically derived for the optimum uploading *** simulations verify the design approach.

关键词： Image remote sensing Secured access Energy efficiency Sensor transmit power Secured access design

Unbiased Learning to Rank with Query-Level Click Propensity Estimation: Beyond Pointwise Observation and Relevance

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yu, Lulu Bi, Keping Guo, Jiafeng Liu, Shihao Yin, Dawei Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS University of Chinese Academy of Sciences Beijing China Baidu Inc Beijing China

Most existing unbiased learning-to-rank (ULTR) approaches are based on the user examination hypothesis, which assumes that users will click a result only if it is both relevant and observed (typically modeled by position). However, in real-world scenarios, users often click only one or two results after examining multiple relevant options, due to limited patience or because their information needs have already been satisfied. Motivated by this, we propose a query-level click propensity model to capture the probability that users will click on different result lists, allowing for nonzero probabilities that users may not click on an observed relevant result. We hypothesize that this propensity increases when more potentially relevant results are present, and refer to this user behavior as relevance saturation bias. Our method introduces a Dual Inverse Propensity Weighting (DualIPW) mechanism—combining query-level and position-level IPW—to address both relevance saturation and position bias. Through theoretical derivation, we prove that DualIPW can learn an unbiased ranking model. Experiments on the real-world Baidu-ULTR dataset demonstrate that our approach significantly outperforms state-of-the-art ULTR baselines. The code and dataset information can be found at https://***/Trustworthy-Information-Access/DualIPW. © 2025, CC BY.

关键词： Contrastive Learning