检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language processing, EMNLP 2024

作者： Zhang, Ming Huang, Caishuang Wu, Yilong Liu, Shichun Zheng, Huiyuan Dong, Yurui Shen, Yujiong Dou, Shihan Zhao, Jun Ye, Junjie Zhang, Qi Gui, Tao Huang, Xuanjing School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China Institute of Modern Languages and Linguistics Fudan University China

ISBN: (纸本)9798891761643

Task-oriented dialogue (TOD) systems aim to efficiently handle task-oriented conversations, including information collection. How to utilize TOD accurately, efficiently and effectively for information collection has always been a critical and challenging task. Recent studies have demonstrated that Large Language Models (LLMs) excel in dialogue, instruction generation, and reasoning, and can significantly enhance the performance of TOD through fine-tuning. However, current datasets primarily cater to user-led systems and are limited to predefined specific scenarios and slots, thereby necessitating improvements in the proactiveness, diversity, and capabilities of TOD. In this study, we present a detailed multi-domain task-oriented data construction process for conversations, and a Chinese dialogue dataset generated based on this process, TransferTOD, which authentically simulates human-computer dialogues in 30 popular life service scenarios. Leveraging this dataset, we trained a model using full-parameter fine-tuning called TransferTOD-7B, showcasing notable abilities in slot filling and questioning. Our work has demonstrated its strong generalization capabilities in various downstream scenarios, significantly enhancing both data utilization efficiency and system performance. The data is released in https://***/KongLongGeFDU/TransferTOD. © 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

RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning

RoTBench: A Multi-Level Benchmark for Evaluating the Robustn...

引用

2024 Conference on Empirical Methods in Natural Language processing, EMNLP 2024

作者： Ye, Junjie Wu, Yilong Gao, Songyang Huang, Caishuang Li, Sixian Li, Guanyu Fan, Xiaoran Zhang, Qi Gui, Tao Huang, Xuanjing School of Computer Science Fudan University China Institute of Modern Languages and Linguistics Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

ISBN: (纸本)9798891761643

Tool learning has generated widespread interest as a vital means of interaction between Large Language Models (LLMs) and the physical world. Current research predominantly emphasizes LLMs' capacity to utilize tools in well-structured environments while overlooking their stability when confronted with the inevitable noise of the real world. To bridge this gap, we introduce RoTBench, a multi-level benchmark for evaluating the robustness of LLMs in tool learning. Specifically, we establish five external environments, each featuring varying levels of noise (i.e., Clean, Slight, Medium, Heavy, and Union), providing an in-depth analysis of the model's resilience across three critical phases: tool selection, parameter identification, and content filling. Experiments involving six widely-used models underscore the urgent necessity for enhancing the robustness of LLMs in tool learning. For instance, the performance of GPT-4 even drops significantly from 80.00 to 58.10 when there is no substantial change in manual accuracy. More surprisingly, the noise correction capability inherent in the GPT family paradoxically impedes its adaptability in the face of mild noise. In light of these findings, we propose RoTTuning, a strategy that enriches the diversity of training environments to bolster the robustness of LLMs in tool learning. The code and data are available at https://***/Junjie-Ye/RoTBench. © 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

PDF-to-Tree: Parsing PDF Text Blocks into a Tree

PDF-to-Tree: Parsing PDF Text Blocks into a Tree

引用

2024 Conference on Empirical Methods in Natural Language processing, EMNLP 2024

作者： Zhang, Yue Zhang, Zhihao Lai, Wenbin Zhang, Chong Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University China Institute of Modern Languages and Linguistics Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

ISBN: (纸本)9798891761681

In many PDF documents, the reading order of text blocks is missing, which can hinder machine understanding of the document's content. Existing works try to extract one universal reading order for a PDF file. However, applications, like Retrieval Augmented Generation (RAG), require breaking long articles into sections, subsections and table cells for better indexing. For this reason, this paper introduces a new task and dataset, PDF-to-Tree, which organizes the text blocks of a PDF into a tree structure. Since a PDF may contain thousands of text blocks, this paper proposes a transition-based parser that uses a greedy strategy to build the tree structure. Compared to the parser for plain text, we also use multi-modal features to encode the parser state. Experiments show that our approach achieves an accuracy of 93.93%, surpassing the performance of baseline methods by an improvement of 6.72%. The dataset is public available at https://***/yuezh000/PDFto-Tree. © 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

Improving Discriminative Capability of Reward Models in RLHF Using Contrastive Learning

Improving Discriminative Capability of Reward Models in RLHF...

引用

2024 Conference on Empirical Methods in Natural Language processing, EMNLP 2024

作者： Chen, Lu Zheng, Rui Wang, Binghai Jin, Senjie Huang, Caishuang Ye, Junjie Zhang, Zhihao Zhou, Yuhao Xi, Zhiheng Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University China Institute of Modern Languages and Linguistics Fudan University China Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

ISBN: (纸本)9798891761643

Reinforcement Learning from Human Feedback (RLHF) is a crucial approach to aligning language models with human values and intentions. A fundamental challenge in this method lies in ensuring that the reward model accurately understands and evaluates human preferences. Current methods rely on ranking losses to teach the reward model to assess preferences, but they are susceptible to noise and ambiguous data, often failing to deeply understand human intentions. To address this issue, we introduce contrastive learning into the reward modeling process. In addition to supervised ranking loss, we introduce an unsupervised contrastive loss to enable the reward model to fully capture the distinctions in contrastive data. Experimental results demonstrate that the proposed contrastive learning-based reward modeling method effectively enhances the generalization of the reward model, stabilizes the reinforcement learning training process, and improves the final alignment with human preferences. © 2024 Association for Computational Linguistics.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

LONGAGENT: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration

LONGAGENT: Achieving Question Answering for 128k-Token-Long ...

引用

2024 Conference on Empirical Methods in Natural Language processing, EMNLP 2024

作者： Zhao, Jun Zu, Can Xu, Hao Lu, Yi He, Wei Ding, Yiwen Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China Institute of Modern Languages and Linguistics Fudan University China

ISBN: (纸本)9798891761643

Large language models (LLMs) have achieved tremendous success in understanding language and processing text. However, question-answering (QA) on lengthy documents faces challenges of resource constraints and a high propensity for errors, even for the most advanced models such as GPT-4 and Claude2. In this paper, we introduce LONGAGENT, a multi-agent collaboration method that enables efficient and effective QA over 128k-token-long documents. LONGAGENT adopts a divide- and-conquer strategy, breaking down lengthy documents into shorter, more manageable text chunks. A leader agent comprehends the user's query and organizes the member agents to read their assigned chunks, reasoning a final answer through multiple rounds of discussion. Due to members' hallucinations, it's difficult to guarantee that every response provided by each member is accurate. To address this, we develop an inter-member communication mechanism that facilitates information sharing, allowing for the detection and mitigation of hallucinatory responses. Experimental results show that a LLaMA-2 7B driven by LONGAGENT can effectively support QA over 128k-token documents, achieving 16.42% and 1.63% accuracy gains over GPT-4 on single-hop and multi-hop QA settings, respectively. © 2024 Association for Computational Linguistics.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Tokenizing Features for Fast Video Object Segmentation

Tokenizing Features for Fast Video Object Segmentation

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Meng, Tianfang Zhang, Wei Zhang, Wenqiang Fudan University Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Shanghai China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

This paper investigates how to take full advantage of the tem-poral and spatial information in videos with minimal compu-tational cost in the semi-supervised video object segmentation (VOS) task. Current state-of-the-art methods have achieved remarkable performance by matching features of the current frame with those of past frames to propagate the past segmen-tation masks to the current. However, the inference speeds of such matching-based methods are limited due to the tremen-dous amount of computation on pixel-to-pixel matching. To address this problem, we propose a fast matching mechanism for VOS that extracts essential object information as a handful of token vectors for matching. By extracting succinct but suf-ficient information from the pixel-wise features, we develop a fast VOS model which achieves competitive segmentation performance (81.6% J & F on DAVIS-2017), maintaining a high inference speed (FPS = 42.1). © 2022 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

ChatGPT: potential, prospects, and limitations

引用

Frontiers of information Technology & Electronic Engineering 2024年第1期25卷 6-11页

作者： Jie ZHOU Pei KE Xipeng QIU Minlie HUANG Junping ZHANG School of Computer Science Fudan UniversityShanghai 200433China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Shanghai Key Laboratory of Intelligent Information Processing Shanghai 200433China

Recently,OpenAI released Chat Generative Pre-trained Transformer(ChatGPT)(Schulman et al.,2022)(https://***),which has attracted considerable attention from the industry and academia because of its impressive *** is the first time that such a variety of open tasks can be well solved within one large language *** better understand ChatGPT,we briefly introduce its history,discuss its advantages and disadvantages,and point out several potential ***,we analyze its impact on the development of trustworthy artificial intelligence,conversational search engine,and artificial general intelligence.

关键词： artificial limitations intelligence

来源：评论

学校读者我要写书评

暂无评论

Promoting Students' Programming Skills in Constructions for Teaching Materials and Curriculums: Experiments for Comprehensive Application of Programming Methods

Promoting Students' Programming Skills in Constructions for ...

引用

2022 Global Conference on Robotics, Artificial Intelligence and information Technology, GCRAIT 2022

作者： Wu, Yonghui School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

ISBN: (数字)9781665481922

ISBN: (纸本)9781665481922

The goal for experiments for programming languages is to polish students' programming skills solving problems by programming languages. Programming contests are contests solving problems by programming. A programming language experiment based on 'solving problems by programming' consists of the related knowledge background for programming languages and methods, programming contest problems and their analysis and solutions. The paper specifies experiments for programming languages based on 'solving problems by programming': the comprehensive application of programming methods. These experiments enlighten students to solve a problem by programming through comprehensively applying programming methods: offline method, binary search, and real precision processing. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Efficiently Learning Significant Fourier Feature Pairs for Statistical Independence Testing 38

Efficiently Learning Significant Fourier Feature Pairs for S...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Ren, Yixin Xia, Yewei Zhang, Hao Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Department of Computer Science and Technology Tongji University Shanghai China SIAT Chinese Academy of Sciences Shenzhen China Machine Learning Department MBZUAI Abu Dhabi United Arab Emirates

We propose a novel method to efficiently learn significant Fourier feature pairs for maximizing the power of Hilbert-Schmidt Independence Criterion (HSIC) based independence tests. We first reinterpret HSIC in the frequency domain, which reveals its limited discriminative power due to the inability to adapt to specific frequency-domain features under the current inflexible configuration. To remedy this shortcoming, we introduce a module of learnable Fourier features, thereby developing a new criterion. We then derive a finite sample estimate of the test power by modeling the behavior of the criterion, thus formulating an optimization objective for significant Fourier feature pairs learning. We show that this optimization objective can be computed in linear time (with respect to the sample size n), which ensures fast independence tests. We also prove the convergence property of the optimization objective and establish the consistency of the independence tests. Extensive empirical evaluation on both synthetic and real datasets validates our method's superiority in effectiveness and efficiency, particularly in handling high-dimensional data and dealing with large-scale scenarios. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Brain-inspired artificial intelligence research: A review

引用

science China(Technological sciences) 2024年第8期67卷 2282-2296页

作者： WANG GuoYin BAO HuaNan LIU Qun ZHOU TianGang WU Si HUANG TieJun YU ZhaoFei LU CeWu GONG YiHong ZHANG ZhaoXiang HE Sheng Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and TelecommunicationsChongqing 400065China College of Computer and Information Science Chongqing Normal UniversityChongqing 401331China State Key Laboratory of Brain and Cognitive Science Institute of BiophysicsChinese Academy of SciencesBeijing 100101China School of Psychological and Cognitive Sciences Peking UniversityBeijing 100871China State Key Laboratory of Multimedia Information Processing School of Computer SciencePeking UniversityBeijing 100871China Department of Computer Science School of ElectronicsInformation and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Faculty of Electronic and Information Engineering Xi’an Jiaotong UniversityXi’an 710049China The Center for Research on Intelligent Perception and Computing Institute of AutomationChinese Academy of SciencesBeijing 100190China Institute of Biophysics Chinese Academy of SciencesBeijing 100101China

Artificial intelligence(AI) systems surpass certain human intelligence abilities in a statistical sense as a whole, but are not yet the true realization of these human intelligence abilities and behaviors. There are differences, and even contradictions, between the cognition and behavior of AI systems and humans. With the goal of achieving general AI, this study contains a review of the role of cognitive science in inspiring the development of the three mainstream academic branches of AI based on the three-layer framework proposed by David Marr, and the limitations of the current development of AI are explored and analyzed. The differences and inconsistencies between the cognition mechanisms of the human brain and the computation mechanisms of AI systems are analyzed. They are found to be the cause of the differences and contradictions between the cognition and behavior of AI systems and humans. Additionally, eight important research directions and their scientific issues that need to focus on braininspired AI research are proposed: highly imitated bionic information processing, a large-scale deep learning model that balances structure and function, multi-granularity joint problem solving bidirectionally driven by data and knowledge, AI models that simulate specific brain structures, a collaborative processing mechanism with the physical separation of perceptual processing and interpretive analysis, embodied intelligence that integrates the brain cognitive mechanism and AI computation mechanisms,intelligence simulation from individual intelligence to group intelligence(social intelligence), and AI-assisted brain cognitive intelligence.

关键词： artificial intelligence cognitive science brain science intelligence science large language model

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：