检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

7,582 篇 会议
71 册 图书
49 篇 期刊文献
2 篇 学位论文

馆藏范围

7,703 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

6,480 篇 工学
- 6,252 篇 计算机科学与技术...
- 3,600 篇 软件工程
- 748 篇 信息与通信工程
- 507 篇 控制科学与工程
- 271 篇 电气工程
- 213 篇 生物工程
- 121 篇 化学工程与技术
- 100 篇 机械工程
- 85 篇 电子科学与技术（可...
- 76 篇 生物医学工程（可授...
- 63 篇 安全科学与工程
- 59 篇 农业工程
- 57 篇 交通运输工程
- 49 篇 网络空间安全
1,524 篇 管理学
- 1,167 篇 图书情报与档案管...
- 467 篇 管理科学与工程(可...
- 134 篇 工商管理
1,472 篇 文学
- 1,465 篇 外国语言文学
- 161 篇 中国语言文学
1,447 篇 理学
- 775 篇 数学
- 352 篇 物理学
- 250 篇 生物学
- 240 篇 统计学（可授理学、...
- 120 篇 化学
- 101 篇 系统科学
165 篇 法学
- 153 篇 社会学
130 篇 医学
- 94 篇 临床医学
- 76 篇 基础医学(可授医学...
112 篇 教育学
- 106 篇 教育学
68 篇 农学
- 68 篇 作物学
42 篇 经济学
6 篇 哲学
3 篇 艺术学
1 篇 军事学

主题

1,183 篇 natural language...
872 篇 computational li...
621 篇 natural language...
283 篇 semantics
165 篇 natural language...
128 篇 machine learning
127 篇 graphic methods
123 篇 iterative method...
111 篇 sentiment analys...
110 篇 speech recogniti...
106 篇 deep learning
94 篇 syntactics
90 篇 text processing
86 篇 speech processin...
81 篇 embeddings
72 篇 information retr...
69 篇 modeling languag...
69 篇 artificial intel...
66 篇 contrastive lear...
63 篇 zero-shot learni...

机构

74 篇 carnegie mellon ...
36 篇 national univers...
34 篇 carnegie mellon ...
34 篇 language technol...
34 篇 institute for na...
33 篇 university of wa...
33 篇 school of comput...
32 篇 tsinghua univers...
30 篇 nanyang technolo...
30 篇 stanford univers...
30 篇 university of ch...
29 篇 zhejiang univers...
27 篇 alibaba grp peop...
26 篇 carnegie mellon ...
25 篇 gaoling school o...
25 篇 harbin institute...
25 篇 peking universit...
25 篇 natl univ singap...
24 篇 allen inst artif...
23 篇 the chinese univ...

作者

42 篇 neubig graham
39 篇 zhou guodong
39 篇 smith noah a.
36 篇 liu yang
36 篇 lapata mirella
34 篇 sun maosong
32 篇 zhang min
30 篇 liu qun
30 篇 hovy eduard
29 篇 zhao jun
27 篇 schütze hinrich
27 篇 liu zhiyuan
26 篇 gurevych iryna
25 篇 vulic ivan
22 篇 huang xuanjing
21 篇 chang kai-wei
21 篇 liu kang
21 篇 zhang yue
20 篇 wen ji-rong
20 篇 zhang qi

语言

6,985 篇 英文
689 篇 其他
23 篇 中文
8 篇 法文
4 篇 土耳其文
2 篇 德文
2 篇 俄文

检索条件"任意字段=Proceedings of the Conference on Empirical Methods in Natural Language Processing"

共 7704 条记录，以下是331-340 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

A Probability-Quality Trade-off in Aligned language Models and its Relation to Sampling Adaptors

A Probability-Quality Trade-off in Aligned Language Models a...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Tan, Naaman Valvoda, Josef Liu, Tianyu Svete, Anej Qin, Yanxia Min-Yen, Kan Cotterell, Ryan National University of Singapore Singapore University of Copenhagen Denmark ETH Zürich Switzerland

ISBN: (纸本)9798891761643

The relationship between the quality of a string, as judged by a human reader, and its probability, p(y) under a language model undergirds the development of better language models. For example, many popular algorithms for sampling from a language model have been conceived with the goal of manipulating p(y) to place higher probability on strings that humans deem of high quality (Fan et al., 2018;Holtzman et al., 2020). In this article, we examine the probability-quality relationship in language models explicitly aligned to human preferences, e.g., through reinforcement learning through human feedback. We show that, when sampling corpora from an aligned language model, there exists a trade-off between the strings' average reward and average log-likelihood under the prior language model, i.e., the same model before alignment with human preferences. We provide a formal treatment of this phenomenon and demonstrate how a choice of sampling adaptor allows for a selection of how much likelihood we exchange for the reward. © 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

Universal Vulnerabilities in Large language Models: Backdoor Attacks for In-context Learning

Universal Vulnerabilities in Large Language Models: Backdoor...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Zhao, Shuai Jia, Meihuizi Tuan, Luu Anh Pan, Fengjun Wen, Jinming Nanyang Technological University Singapore Guangzhou University Guangzhou China Beijing Institute of Technology Beijing China

ISBN: (纸本)9798891761643

In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite being widely applied, in-context learning is vulnerable to malicious attacks. In this work, we raise security concerns regarding this paradigm. Our studies demonstrate that an attacker can manipulate the behavior of large language models by poisoning the demonstration context, without the need for fine-tuning the model. Specifically, we design a new backdoor attack method, named ICLAttack, to target large language models based on in-context learning. Our method encompasses two types of attacks: poisoning demonstration examples and poisoning demonstration prompts, which can make models behave in alignment with predefined intentions. ICLAttack does not require additional fine-tuning to implant a backdoor, thus preserving the model's generality. Furthermore, the poisoned examples are correctly labeled, enhancing the natural stealth of our attack method. Extensive experimental results across several language models, ranging in size from 1.3B to 180B parameters, demonstrate the effectiveness of our attack method, exemplified by a high average attack success rate of 95.0% across the three datasets on OPT models. © 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

Investigating Efficiently Extending Transformers for Long Input Summarization

Investigating Efficiently Extending Transformers for Long In...

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Phang, Jason Zhao, Yao Liu, Peter J. NYU New York NY 10003 USA Google Res Brain Team Mountain View CA USA Google Mountain View CA USA

ISBN: (纸本)9798891760608

While large pretrained Transformer models have proven highly capable at tackling natural language tasks, handling long sequence inputs still poses a significant challenge. One such task is long input summarization, where inputs are longer than the maximum input context of most models. Through an extensive set of experiments, we investigate what model architectural changes and pretraining paradigms most efficiently adapt a pretrained Transformer for long input summarization. We find that a staggered, block-local Transformer with global encoder tokens strikes a good balance of performance and efficiency, and that an additional pretraining phase on long sequences meaningfully improves downstream summarization performance. Based on our findings, we introduce PEGASUS-X, an extension of the PEGASUS model with additional long input pretraining to handle inputs of up to 16K tokens, which achieves strong performance on long input summarization tasks comparable with much larger models.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Images Speak Louder than Words: Understanding and Mitigating Bias in Vision-language Model from a Causal Mediation Perspective

Images Speak Louder than Words: Understanding and Mitigating...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Weng, Zhaotian Gao, Zijun Andrews, Jerone Zhao, Jieyu University of Southern California United States Sony AI

ISBN: (纸本)9798891761643

Vision-language models (VLMs) pre-trained on extensive datasets can inadvertently learn biases by correlating gender information with specific objects or scenarios. Current methods, which focus on modifying inputs and monitoring changes in the model's output probability scores, often struggle to comprehensively understand bias from the perspective of model components. We propose a framework that incorporates causal mediation analysis to measure and map the pathways of bias generation and propagation within VLMs. Our framework is applicable to a wide range of vision-language and multimodal tasks. In this work, we apply it to the object detection task and implement it on the GLIP model. This approach allows us to identify the direct effects of interventions on model bias and the indirect effects of interventions on bias mediated through different model components. Our results show that image features are the primary contributors to bias, with significantly higher impacts than text features, specifically accounting for 32.57% and 12.63% of the bias in the MSCOCO and PASCAL-SENTENCE datasets, respectively. Notably, the image encoder's contribution surpasses that of the text encoder and the deep fusion encoder. Further experimentation confirms that contributions from both language and vision modalities are aligned and non-conflicting. Consequently, focusing on blurring gender representations within the image encoder which contributes most to the model bias, reduces bias efficiently by 22.03% and 9.04% in the MSCOCO and PASCAL-SENTENCE datasets, respectively, with minimal performance loss or increased computational demands. © 2024 Association for Computational Linguistics.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in language Models

Language Models as Compilers: Simulating Pseudocode Executio...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Chae, Hyungjoo Kim, Yeonghyeon Kim, Seungone Ong, Kai Tzu-Iunn Kwak, Beong-Woo Kim, Moohyeon Kim, Seonghwan Kwon, Taeyoon Moon, Seungjun Chung, Jiwan Yu, Youngjae Yeo, Jinyoung Yonsei University Korea Republic of Carnegie Mellon University United States

ISBN: (纸本)9798891761643

Algorithmic reasoning tasks that involve complex logical patterns, such as completing Dyck language, pose challenges for large language models (LLMs), despite their recent success. Prior work has used LLMs to generate programming language and applied external compilers for such tasks. Yet, when on the fly, it is hard to generate an executable code with the correct logic for the solution. Even so, code for one instance cannot be reused for others, although they might require the same logic to solve. We present THINK-AND-EXECUTE, a novel framework that improves LLMs' algorithmic reasoning: (1) In THINK, we discover task-level logic shared across all instances, and express such logic with pseudocode;(2) In EXECUTE, we tailor the task-level pseudocode to each instance and simulate the execution of it. THINK-AND-EXECUTE outperforms several strong baselines (including CoT and PoT) in diverse algorithmic reasoning tasks. We manifest the advantage of using task-level pseudocode over generating instance-specific solutions one by one. Also, we show that pseudocode can better improve LMs' reasoning than natural language guidance, even though they are trained with natural language instructions. © 2024 Association for Computational Linguistics.

关键词： Computer circuits

来源：评论

学校读者我要写书评

暂无评论

Unlocking Memorization in Large language Models with Dynamic Soft Prompting

Unlocking Memorization in Large Language Models with Dynamic...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Wang, Zhepeng Bao, Runxue Wu, Yawen Taylor, Jackson Xiao, Cao Zheng, Feng Jiang, Weiwen Gao, Shangqian Zhang, Yanfu George Mason University United States GE Healthcare United States University of Pittsburgh United States William and Mary United States Southern University of Science and Technology China Florida State University United States

ISBN: (纸本)9798891761643

Pretrained large language models (LLMs) have excelled in a variety of natural language processing (NLP) tasks, including summarization, question answering, and translation. However, LLMs pose significant security risks due to their tendency to memorize training data, leading to potential privacy breaches and copyright infringement. Therefore, accurate measurement of the memorization is essential to evaluate and mitigate these potential risks. However, previous attempts to characterize memorization are constrained by either using prefixes only or by prepending a constant soft prompt to the prefixes, which cannot react to changes in input. To address this challenge, we propose a novel method for estimating LLM memorization using dynamic, prefix-dependent soft prompts. Our approach involves training a transformer-based generator to produce soft prompts that adapt to changes in input, thereby enabling more accurate extraction of memorized data. Our method not only addresses the limitations of previous methods but also demonstrates superior performance in diverse experimental settings compared to state-of-the-art techniques. In particular, our method can achieve the maximum relative improvement of 135.3% and 39.8% over the vanilla baseline on average in terms of discoverable memorization rate for the text generation task and code generation task, respectively. Our code is available at https://***/wangger/llmmemorization-dsp. © 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

Scaling Parameter-Constrained language Models with Quality Data

Scaling Parameter-Constrained Language Models with Quality D...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Chang, Ernie Paltenghi, Matteo Li, Yang Lin, Pin-Jie Zhao, Changsheng Huber, Patrick Liu, Zechun Rabatin, Rastislav Shi, Yangyang Chandra, Vikas AI at Meta United States Iowa State University United States Virginia Tech United States

ISBN: (纸本)9798891761667

Scaling laws in language modeling traditionally quantify training loss as a function of dataset size and model parameters, providing compute-optimal estimates but often neglecting the impact of data quality on model generalization. In this paper, we extend the conventional understanding of scaling law by offering a microscopic view of data quality within the original formulation – effective training tokens – which we posit to be a critical determinant of performance for parameter-constrained language models. Specifically, we formulate the proposed term of effective training tokens to be a combination of two readily-computed indicators of text: (i) text diversity and (ii) syntheticity as measured by a teacher model. We pretrained over 200 models of 25M to 1.5B parameters on a diverse set of sampled, synthetic data, and estimated the constants that relate text quality, model size, training tokens, and eight reasoning task accuracy scores. We demonstrated the estimated constants yield +0.83 Pearson correlation with true accuracies, and analyzed it in scenarios involving widely-used data techniques such as data sampling and synthesis which aim to improve data quality. © 2024 Association for Computational Linguistics.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

On the In-context Generation of language Models

On the In-context Generation of Language Models

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Jiang, Zhongtao Zhang, Yuanzhe Luo, Kun Yuan, Xiaowei Zhao, Jun Liu, Kang The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Beijing Academy of Artificial Intelligence China Shanghai Artificial Intelligence Laboratory China

ISBN: (纸本)9798891761643

Large language models (LLMs) are found to have the ability of in-context generation (ICG): when they are fed with an in-context prompt concatenating a few somehow similar examples, they can implicitly recognize the pattern of them and then complete the prompt in the same pattern. ICG is curious, since language models are usually not explicitly trained in the same way as the in-context prompt, and the distribution of examples in the prompt differs from that of sequences in the pretrained corpora. This paper provides a systematic study of the ICG ability of language models, covering discussions about its source and influential factors, in the view of both theory and empirical experiments. Concretely, we first propose a plausible latent variable model to model the distribution of the pretrained corpora, and then formalize ICG as a problem of next topic prediction. With this framework, we can prove that the repetition nature of a few topics ensures the ICG ability on them theoretically. Then, we use this controllable pretrained distribution to generate several medium-scale synthetic datasets (token scale: 2.1B~3.9B) and experiment with different settings of Transformer architectures (parameter scale: 4M~234M). Our experimental results further offer insights into how the data and model architectures influence ICG. © 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

Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large language Models

Whispers that Shake Foundations: Analyzing and Mitigating Fa...

引用

2024 conference on empirical methods in natural language processing, EMNLP 2024

作者： Yuan, Hongbang Cao, Pengfei Jin, Zhuoran Chen, Yubo Zeng, Daojian Liu, Kang Zhao, Jun The Key Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Hunan Normal University Changsha China

ISBN: (纸本)9798891761643

Large language Models (LLMs) have shown impressive capabilities but still suffer from the issue of hallucinations. A significant type of this issue is the false premise hallucination, which we define as the phenomenon when LLMs generate hallucinated text when confronted with false premise questions. In this paper, we perform a comprehensive analysis of the false premise hallucination and elucidate its internal working mechanism: a small subset of attention heads (which we designate as false premise heads) disturb the knowledge extraction process, leading to the occurrence of false premise hallucination. Based on our analysis, we propose FAITH (False premise Attention head constraIining for miTigating Hallucinations), a novel and effective method to mitigate false premise hallucinations. It constrains the false premise attention heads during the model inference process. Impressively, extensive experiments demonstrate that constraining only approximately 1% of the attention heads in the model yields a notable increase of nearly 20% of model performance. © 2024 Association for Computational Linguistics.

关键词：

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

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 30 31 32 33 34 35 36 37 38 39 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：