检索结果-内蒙古大学图书馆

23rd China National Conference on Computational Linguistics, CCL 2024

作者： Xu, Ruoxi Lin, Hongyu Guan, Xinyan Sun, Yingfei Sun, Le University of Chinese Academy of Sciences Beijing101408 China Chinese Information Processing Laboratory Institute of Software Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9789819783663

Understanding documents is central to many real-world tasks but remains a challenging topic. Unfortunately, there is no well-established consensus on how to comprehensively evaluate document understanding abilities, which significantly hinders the fair comparison and measuring the progress of the field. To benchmark document understanding researches, this paper summarizes four representative abilities, i.e., document classification, document structural analysis, document information extraction, and document transcription. Under the new evaluation framework, we propose Document Language Understanding Evaluation – DLUE, a new task suite which covers a wide-range of tasks in various forms, domains and document genres. We also systematically evaluate six well-established transformer models and representative LLMs on DLUE, and find that due to the lengthy content, complicated underlying structure and dispersed knowledge, document understanding is still far from being solved in complex real-world scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Position: Building Guardrails for Large Language Models Requires Systematic Design 41

Position: Building Guardrails for Large Language Models Requ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Dong, Yi Mu, Ronghui Jin, Gaojie Qi, Yi Hu, Jinwei Zhao, Xingyu Meng, Jie Ruan, Wenjie Huang, Xiaowei Department of Computer Science University of Liverpool United Kingdom State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China WMG University of Warwick Warwick United Kingdom Institute of Digital Technologies Loughborough University London United Kingdom

As Large Language Models (LLMs) become more integrated into our daily lives, it is crucial to identify and mitigate their risks, especially when the risks can have profound impacts on human users and societies. Guardrails, which filter the inputs or outputs of LLMs, have emerged as a core safeguarding technology. This position paper takes a deep look at current open-source solutions (Llama Guard, Nvidia NeMo, Guardrails AI), and discusses the challenges and the road towards building more complete solutions. Drawing on robust evidence from previous research, we advocate for a systematic approach to construct guardrails for LLMs, based on comprehensive consideration of diverse contexts across various LLMs applications. We propose employing sociotechnical methods through collaboration with a multi-disciplinary team to pinpoint precise technical requirements, exploring advanced neural-symbolic implementations to embrace the complexity of the requirements, and developing verification and testing to ensure the utmost quality of the final product. Copyright 2024 by the author(s)

关键词： Guard rails

来源：评论

学校读者我要写书评

暂无评论

Open Grounded Planning: Challenges and Benchmark Construction 62

Open Grounded Planning: Challenges and Benchmark Constructio...

引用

62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Guo, Shiguang Deng, Ziliang Lin, Hongyu Lu, Yaojie Han, Xianpei Sun, Le Chinese Information Processing Laboratory China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Key Laboratory of System Software Chinese Academy of Sciences China

ISBN: (纸本)9798891760943

The emergence of large language models (LLMs) has increasingly drawn attention to the use of LLMs for human-like planning. Existing work on LLM-based planning either focuses on leveraging the inherent language generation capabilities of LLMs to produce free-style plans or employs reinforcement learning approaches to learn decision-making for a limited set of actions within restricted environments. However, both approaches exhibit significant discrepancies between the open and executable requirements in real-world planning. In this paper, we propose a new planning task-open grounded planning. The primary objective of open grounded planning is to ask the model to generate an executable plan based on a variable action set, thereby ensuring the executability of the produced plan. To this end, we establish a benchmark for open grounded planning spanning a wide range of domains. Then we test current state-of-the-art LLMs along with five planning approaches, revealing that existing LLMs and methods still struggle to address the challenges posed by grounded planning in open domains. The outcomes of this paper define and establish a foundational dataset for open grounded planning, and shed light on the potential challenges and future directions of LLM-based planning. Our code and datasets are at https://***/Shiguang-Guo/Open-Grounded-Planning. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Formally Verifying Arithmetic Chisel Designs for All Bit Widths at Once 24

Formally Verifying Arithmetic Chisel Designs for All Bit Wid...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Feng, Weizhi Liu, Yicheng Liu, Jiaxiang Jansen, David N Zhang, Lijun Wu, Zhilin State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Shenzhen University Shenzhen China

ISBN: (纸本)9798400706011

Chisel is an open-source hardware description language embedded in Scala to facilitate parameterized and reusable digital circuit design. Chisel is becoming increasingly popular and has been used to design RISC-V CPUs, e.g. RocketChip and XiangShan. While Chisel features high-level hardware designs, its verification is still low-level: Low-level (e.g. Verilog) programs are first generated from Chisel programs, then the verification tools are applied to these low-level programs. In this work, we focus on formal verification of arithmetic units. Efficient low-level formal verification of arithmetic units has always been a challenge and remains an active research area, attributed to the state explosion problem brought on by bit widths. To circumvent this problem for arithmetic Chisel designs, we propose an approach to their high-level formal verification so that their correctness is verified for all bit widths at once, instead of for each bit width separately. The key idea is to transform arithmetic Chisel designs into Scala software programs that simulate their behaviors, where the high-level features are preserved, then resort to Stainless, a deductive formal verification tool for Scala. We validate the effectiveness of this approach by formally verifying the correctness of dividers and multipliers in two representative open source RISC-V processors, namely, RocketChip and XiangShan. Compared to the existing proof-assistant-based parameterized verification approaches for arithmetic designs (e.g. Kami), the verification cost in our approach is much lower on average. © 2024 Copyright held by the owner/author(s).

关键词： Formal verification

来源：评论

学校读者我要写书评

暂无评论

Computable one-way functions on the reals

arXiv

引用

arXiv 2024年

作者： Barmpalias, George Zhang, Xiaoyan State Key Lab of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

A major open problem in computational complexity is the existence of a one-way function, namely a function from strings to strings which is computationally easy to compute but hard to invert. Levin (2023) formulated the notion of one-way functions from reals (infinite bit-sequences) to reals in terms of computability, and asked whether partial computable one-way functions exist. We give a strong positive answer using the hardness of the halting problem and exhibiting a total computable one-way function. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Dimensionality and randomness

arXiv

引用

arXiv 2024年

作者： Barmpalias, George Zhang, Xiaoyan State Key Lab of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

Arranging the bits of a random string or real into k columns of a two-dimensional array or higher dimensional structure is typically accompanied with loss in the Kolmogorov complexity of the columns, which depends on k. We quantify and characterize this phenomenon for arrays and trees and its relationship to negligible classes. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

PLAME: Piecewise-Linear Approximate Measure for Additive Kernel SVM (Extended abstract) 40

PLAME: Piecewise-Linear Approximate Measure for Additive Ker...

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Chan, Tsz Nam Li, Zhe Leong Hou, U. Cheng, Reynold Shenzhen University Department of Computer Science and Software Engineering China Alibaba Cloud University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science China The University of Hong Kong Department of Computer Science and Musketeers Foundation Institute of Data Science Hong Kong

ISBN: (纸本)9798350317152

Additive Kernel SVM has been extensively used in many applications, including human activity detection and pedestrian detection. Since training an additive kernel SVM model is very time-consuming, which is not scalable to largescale datasets, many efficient solutions have been developed in the past few years. However, most of the existing methods normally fail to achieve one of these three important conditions which are (1) low classification error, (2) low memory space, and (3) low training time. In order to simultaneously fulfill these three conditions, we develop the new piecewise-linear approximate measure (PLAME) for training additive kernel SVM models. Experimental results verify that this approach can achieve the best trade-off between accuracy, memory space, and training time compared with different types of state-of-the-art methods. © 2024 IEEE.

关键词： Additives

来源：评论

学校读者我要写书评

暂无评论

FFT-based efficient Poisson solver in nonrectangular domain

FFT-based efficient Poisson solver in nonrectangular domain

引用

作者： Wang, Yunong Hou, Fei Wang, Wencheng State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Poisson's equation is one of the most popular partial differential equation (PDE), which is widely used in image processing, computer graphics and other fields. However, solving a large-scale Poisson's equation always costs huge computational resources. Fast Fourier transform (FFT) is an efficient Poisson solver but it only works in rectangular domain. In this paper, we propose a FFT-based Poisson solver in nonrectangular domain on regular grids combined with algebraic multigrid (AMG). We extend the original Poisson's equation to a rectangular domain to construct an equivalent equation, so that it can use FFT algorithm to accelerate the solving to Poisson's equation. Experiments show that the FFT-based Poisson solver can improve the solving speed of large-scale Poisson's equations in nonrectangular domain. We demonstrate the solver in applications of image processing and fluid simulation. © 2023 John Wiley & Sons Ltd.

关键词： Poisson equation

来源：评论

学校读者我要写书评

暂无评论

RAT: A Refactoring-Aware Tool for Tracking Code History 24

RAT: A Refactoring-Aware Tool for Tracking Code History

引用

46th International Conference on software Engineering: Companion, ICSE-Companion 2024

作者： Niu, Feifei Shao, Junqian Xu, Chaofan Mayr-Dorn, Christoph Assunção, Wesley K. G. Huang, Liguo Li, Chuanyi Ge, Jidong Luo, Bin Egyed, Alexander State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Institute for Software Systems Engineering Johannes Kepler University Linz Austria Department of Computer Science North Carolina State University North Carolina United States Department of Computer Science and Engineering Southern Methodist University DallasTX United States

ISBN: (纸本)9798400705021

History of code elements is essential for software maintenance tasks. However, code refactoring is one of the main causes that makes obtaining a consistent view on code evolution difficult as renaming or moving source code elements break such history. To this end, this paper presents RAT, a refactoring-aware tool for keeping track of code elements evolution across time, not just in terms of revisions but also in terms of refactoring. This is the first tool that enables fine-grained code element traceability of the whole repository. Empirical evaluation of leveraging our tool in three bug localization techniques relying on code history shows significant improvement in localization accuracy. Based on our findings, we believe that many of the state-of-the-art approaches using past source code data would benefit from our tool. Demo Tool: https://***/feifeiniu-se/RAT-Demo. Demo Video: https://***/VI-xwUaIPp4. © 2024 IEEE computer Society. All rights reserved.

关键词： Rats

来源：评论

学校读者我要写书评

暂无评论

Detecting Semantic-level Polysemy Ambiguity by Fusing External Semantic Knowledge 36

Detecting Semantic-level Polysemy Ambiguity by Fusing Extern...

引用

36th International Conference on software Engineering and Knowledge Engineering, SEKE 2024

作者： Yang, Huishan Peng, Fengyong Wu, Xi Zhao, Yongxin Li, Yongjian Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China The University of Sydney Australia State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

ISBN: (纸本)1891706594

Sentence with polysemous words can easily be interpreted as different meanings by different people even in a specific context, which will significantly reduce the quality of requirements documents. However, existing ambiguity detection mainly considers the sentence structure and cannot solve this problem well. In this paper, we consider sentence semantics and perform sentence ambiguity detection by introducing external semantic knowledge to explicitly modeling the different semantics of polysemy. Specifically, we determine the target polysemy in the given sentence according to the ambiguous vocabulary list. Furthermore, based on the fusion strategy we designed, we model the different semantics of polysemous word by introducing external semantic knowledge and predict the possible semantics of the sentence by measuring the the gap between different semantic fusion results and the original sentence. This is also the first work to introduce external semantic knowledge into ambiguity detection. The experimental results illustrate that our accuracy is higher than the baseline accuracy of ambiguity in existing research. © 2024 Knowledge Systems institute Graduate School. All rights reserved.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：