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

14,463 篇 会议
654 篇 期刊文献
101 册 图书
40 篇 学位论文
1 篇 科技报告

馆藏范围

15,258 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

10,944 篇 工学
- 10,283 篇 计算机科学与技术...
- 5,408 篇 软件工程
- 1,463 篇 信息与通信工程
- 954 篇 电气工程
- 880 篇 控制科学与工程
- 446 篇 生物工程
- 221 篇 网络空间安全
- 220 篇 化学工程与技术
- 186 篇 机械工程
- 174 篇 生物医学工程（可授...
- 142 篇 电子科学与技术（可...
- 101 篇 仪器科学与技术
- 99 篇 安全科学与工程
2,473 篇 理学
- 1,150 篇 数学
- 649 篇 物理学
- 518 篇 生物学
- 391 篇 统计学（可授理学、...
- 241 篇 系统科学
- 232 篇 化学
2,416 篇 管理学
- 1,748 篇 图书情报与档案管...
- 757 篇 管理科学与工程(可...
- 239 篇 工商管理
- 104 篇 公共管理
1,761 篇 文学
- 1,709 篇 外国语言文学
- 184 篇 中国语言文学
510 篇 医学
- 299 篇 临床医学
- 283 篇 基础医学(可授医学...
- 111 篇 公共卫生与预防医...
276 篇 法学
- 248 篇 社会学
237 篇 教育学
- 224 篇 教育学
100 篇 农学
96 篇 经济学
9 篇 艺术学
7 篇 哲学
4 篇 军事学

主题

3,535 篇 natural language...
1,768 篇 natural language...
952 篇 computational li...
740 篇 semantics
681 篇 machine learning
609 篇 deep learning
520 篇 natural language...
347 篇 computational mo...
338 篇 training
333 篇 accuracy
331 篇 sentiment analys...
329 篇 large language m...
321 篇 feature extracti...
311 篇 data mining
290 篇 speech processin...
260 篇 speech recogniti...
252 篇 transformers
235 篇 neural networks
217 篇 iterative method...
212 篇 support vector m...

机构

85 篇 carnegie mellon ...
51 篇 university of ch...
45 篇 tsinghua univers...
45 篇 carnegie mellon ...
43 篇 zhejiang univers...
43 篇 national univers...
38 篇 nanyang technolo...
36 篇 university of wa...
35 篇 univ chinese aca...
34 篇 university of sc...
34 篇 carnegie mellon ...
33 篇 stanford univers...
32 篇 gaoling school o...
32 篇 school of artifi...
32 篇 alibaba grp peop...
29 篇 tsinghua univ de...
28 篇 harbin institute...
27 篇 language technol...
27 篇 peking universit...
26 篇 microsoft resear...

作者

55 篇 zhou guodong
50 篇 neubig graham
46 篇 liu yang
39 篇 sun maosong
36 篇 zhang min
34 篇 liu qun
33 篇 smith noah a.
28 篇 schütze hinrich
27 篇 liu zhiyuan
27 篇 lapata mirella
26 篇 wen ji-rong
24 篇 chang kai-wei
23 篇 zhou jie
23 篇 yang diyi
23 篇 zhao hai
23 篇 zhao wayne xin
21 篇 chua tat-seng
20 篇 dredze mark
18 篇 biemann chris
18 篇 fung pascale

语言

14,662 篇 英文
482 篇 其他
106 篇 中文
18 篇 法文
15 篇 土耳其文
2 篇 西班牙文
2 篇 俄文

检索条件"任意字段=Conference on empirical methods in natural language processing"

共 15259 条记录，以下是741-750 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：

Large language Models Can Self-Improve

Large Language Models Can Self-Improve

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Huang, Jiaxin Gu, Shixiang Shane Hou, Le Wu, Yuexin Wang, Xuezhi Yu, Hongkun Han, Jiawei Univ Illinois Champaign IL USA Google Mountain View CA 94043 USA

ISBN: (纸本)9798891760608

Large language Models (LLMs) have achieved excellent performances in various tasks. However, fine-tuning an LLM requires extensive supervision. Human, on the other hand, may improve their reasoning abilities by self-thinking without external inputs. In this work, we demonstrate that an LLM is also capable of self-improving with only unlabeled datasets. We use a pre-trained LLM to generate "high-confidence" rationale-augmented answers for unlabeled questions using Chain-of-Though (CoT) prompting and self-consistency, and fine-tune the LLM using those self-generated solutions as target outputs. We show that without any ground truth label, our approach significantly improves the general reasoning ability of PaLM 540B model (74.4%-> 82.1% on GSM8K, 90.0%-> 94.4% on OpenBookQA, and 63.4%-> 67.9% on ANLI-A3) and can also be adapted to extreme low-resource cases where even training questions and CoT prompts are limited. We conduct ablation studies and show that fine-tuning on diverse reasoning paths is critical for self-improvement.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Lost in Translation: Chemical language Models and the Misunderstanding of Molecule Structures

Lost in Translation: Chemical Language Models and the Misund...

引用

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

作者： Ganeeva, Veronika Sakhovskiy, Andrey Khrabrov, Kuzma Savchenko, Andrey Kadurin, Artur Tutubalina, Elena AIRI Sber AI Skoltech Russia HSE University Russia Sber AI Lab Russia ISP RAS Research Center for Trusted Artificial Intelligence Russia

ISBN: (纸本)9798891761681

The recent integration of chemistry with natural language processing (NLP) has advanced drug discovery. Molecule representation in language models (LMs) is crucial in enhancing chemical understanding. We propose Augmented Molecular Retrieval (♡AMORE), a flexible zero-shot framework that assesses trustworthiness of Chemical LMs of different natures: trained solely on molecules for chemical tasks and on a combined corpus of natural language texts and string-based structures. The framework relies on molecule augmentations that preserve an underlying chemical, such as kekulization and cycle replacements. We evaluate encoder-only and generative LMs by calculating a metric based on the similarity score between distributed representations of molecules and their augmentations. Our experiments on ChEBI-20 and QM9 benchmarks show that these models exhibit significantly lower scores than graph-based molecular models trained without language modeling objectives. Augmentation of SMILES representations leads to decreased performance on chemical property prediction tasks in the MoleculeNet benchmark. Additionally, our results on the molecule captioning task for cross-domain models, MolT5 and Text+Chem T5, demonstrate that our representation-based evaluation metrics significantly correlate with the classical text generation metrics like ROUGE and METEOR. © 2024 Association for Computational Linguistics.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

NLEBench+NorGLM: A Comprehensive empirical Analysis and Benchmark Dataset for Generative language Models in Norwegian

NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benc...

引用

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

作者： Liu, Peng Zhang, Lemei Farup, Terje Lauvrak, Even W. Ingvaldsen, Jon Espen Eide, Simen Gulla, Jon Atle Yang, Zhirong Department of Computer Science Norwegian University of Science and Technology Norway Schibsted Media Norway Jinhua Institute of Zhejiang University China

ISBN: (纸本)9798891761643

Norwegian, spoken by only 5 million population, is under-representative within the most impressive breakthroughs in NLP tasks. To the best of our knowledge, there has not yet been a comprehensive evaluation of the existing language models (LMs) on Norwegian generation tasks during the article writing process. To fill this gap, we 1) compiled the existing Norwegian dataset and pre-trained 4 Norwegian Open language Models varied from parameter scales and architectures, collectively called NorGLM;2) introduced a comprehensive benchmark, NLEBench, for evaluating natural language generation capabilities in Norwegian, encompassing translation and human annotation. Based on the investigation, we find that: 1) the mainstream, English-dominated LM GPT-3.5 has limited capability in understanding the Norwegian context;2) the increase in model parameter scales demonstrates limited impact on the performance of downstream tasks when the pre-training dataset is constrained in size;3) smaller models also demonstrate the reasoning capability through Chain-of-Thought;4) a multi-task dataset that includes synergy tasks can be used to verify the generalizability of LLMs on natural language understanding and, meanwhile, test the interconnectedness of these NLP tasks. We share our resources and code for reproducibility under a CC BY-NC 4.0 license. © 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

Privacy Implications of Retrieval-Based language Models

Privacy Implications of Retrieval-Based Language Models

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Huang, Yangsibo Gupta, Samyak Zhong, Zexuan Li, Kai Chen, Danqi Princeton Univ Princeton NJ 08544 USA

ISBN: (纸本)9798891760608

Retrieval-based language models (LMs) have demonstrated improved interpretability, factuality, and adaptability compared to their parametric counterparts by incorporating retrieved text from external datastores. While it is well known that parametric models are prone to leaking private data, it remains unclear how the addition of a retrieval datastore impacts model privacy. In this work, we present the first study of privacy risks in retrieval-based LMs, particularly kNN-LMs. Our goal is to explore the optimal design and training procedure in domains where privacy is of concern, aiming to strike a balance between utility and privacy. Crucially, we find that kNN-LMs are more susceptible to leaking private information from their private datastore than parametric models. We further explore mitigations of privacy risks: When privacy information is targeted and readily detected in the text, we find that a simple sanitization step would eliminate the risks while decoupling query and key encoders achieves an even better utility-privacy trade-off. Otherwise, we consider strategies of mixing public and private data in both datastore and encoder training. While these methods offer modest improvements, they leave considerable room for future work. Together, our findings provide insights for practitioners to better understand and mitigate privacy risks in retrieval-based LMs1.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

STEREOMAP: Quantifying the Awareness of Human-like Stereotypes in Large language Models

STEREOMAP: Quantifying the Awareness of Human-like Stereotyp...

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Jeoung, Sullam Ge, Yubin Diesner, Jana Univ Illinois Urbana IL 61801 USA

ISBN: (纸本)9798891760608

Large language Models (LLMs) have been observed to encode and perpetuate harmful associations present in the training data. We propose a theoretically grounded framework called STEREOMAP to gain insights into their perceptions of how demographic groups have been viewed by society. The framework is grounded in the Stereotype Content Model (SCM);a well-established theory from psychology. According to SCM, stereotypes are not all alike. Instead, the dimensions of Warmth and Competence serve as the factors that delineate the nature of stereotypes. Based on the SCM theory, STEREOMAP maps LLMs' perceptions of social groups (defined by sociodemographic features) using the dimensions of Warmth and Competence. Furthermore, the framework enables the investigation of keywords and verbalizations of reasoning of LLMs' judgments to uncover underlying factors influencing their perceptions. Our results show that LLMs exhibit a diverse range of perceptions towards these groups, characterized by mixed evaluations along the dimensions of Warmth and Competence. Furthermore, analyzing the reasonings of LLMs, our findings indicate that LLMs demonstrate an awareness of social disparities, often stating statistical data and research findings to support their reasoning. This study contributes to the understanding of how LLMs perceive and represent social groups, shedding light on their potential biases and the perpetuation of harmful associations.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Teaching Small language Models Reasoning through Counterfactual Distillation

Teaching Small Language Models Reasoning through Counterfact...

引用

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

作者： Feng, Tao Li, Yicheng Li, Chenglin Chen, Hao Yu, Fei Zhang, Yin Zhejiang University Hangzhou China Ant Group Hangzhou China

ISBN: (纸本)9798891761643

With the rise of large language models (LLMs), many studies are interested in transferring the reasoning capabilities of LLMs to small language models (SLMs). Previous distillation methods usually utilize the capabilities of LLMs to generate chain-of-thought (CoT) samples and teach SLMs via fine-tuning. However, such a standard distillation approach performs poorly when applied to out-of-distribution (OOD) examples, and the diversity of the generated CoT samples is insufficient. In this work, we propose a novel counterfactual distillation framework. Firstly, we leverage LLMs to automatically generate high-quality counterfactual data. Given an input text example, our method generates a counterfactual example that is very similar to the original input, but its task label has been changed to the desired one. Then, we utilize multi-view CoT to enhance the diversity of reasoning samples. Experiments on four NLP benchmarks show that our approach enhances the reasoning capabilities of SLMs and is more robust to OOD data. We also conduct extensive ablations and sample studies to understand the reasoning capabilities of SLMs. © 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

Self-training language Models for Arithmetic Reasoning

Self-training Language Models for Arithmetic Reasoning

引用

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

作者： Kadlčík, Marek Štefánik, Michal Faculty of Informatics Masaryk University Czech Republic

ISBN: (纸本)9798891761681

Recent language models achieve impressive results in tasks involving complex multistep reasoning, but scaling these capabilities further traditionally requires expensive collection of more annotated data. In this work, we explore the potential of improving models' reasoning capabilities without new data, merely using automated feedback to the validity of their predictions in arithmetic reasoning (self-training). In systematic experimentation across six different arithmetic reasoning datasets, we find that models can substantially improve in both single-round (offline) and online self-training, reaching a correct result in +13.9% and +25.9% more cases, respectively, underlining the importance of actuality of self-training feedback. We further find that in the single-round, offline self-training, traditional supervised training can deliver gains comparable to preference optimization, but in online self-training, preference optimization methods largely outperform supervised training thanks to their superior stability and robustness on unseen types of problems. © 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

Why do LLaVA Vision-language Models Reply to Images in English?

Why do LLaVA Vision-Language Models Reply to Images in Engli...

引用

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

作者： Hinck, Musashi Holtermann, Carolin Olson, Matthew Lyle Schneider, Florian Yu, Sungduk Bhiwandiwalla, Anahita Lauscher, Anne Tseng, Shaoyen Lal, Vasudev Intel Labs United States University of Hamburg Germany

ISBN: (纸本)9798891761681

We uncover a surprising multilingual bias occurring in a popular class of multimodal vision-language models (VLMs). Including an image in the query to a LLaVA-style VLM significantly increases the likelihood of the model returning an English response, regardless of the language of the query. This paper investigates the causes of this loss with a two-pronged approach that combines extensive ablation of the design space with a mechanistic analysis of the models' internal representations of image and text inputs. Both approaches indicate that the issue stems in the language modeling component of the LLaVA model. Statistically, we find that switching the language backbone for a bilingual language model has the strongest effect on reducing this error. Mechanistically, we provide compelling evidence that visual inputs are not mapped to a similar space as text ones, and that intervening on intermediary attention layers can reduce this bias. Our findings provide important insights to researchers and engineers seeking to understand the crossover between multimodal and multilingual spaces, and contribute to the goal of developing capable and inclusive VLMs for non-English contexts. © 2024 Association for Computational Linguistics.

关键词： Structured Query language

来源：评论

学校读者我要写书评

暂无评论

Text Rendering Strategies for Pixel language Models

Text Rendering Strategies for Pixel Language Models

引用

conference on empirical methods in natural language processing (EMNLP)

作者： Lotz, Jonas F. Salesky, Elizabeth Rust, Phillip Elliott, Desmond Univ Copenhagen Dept Comp Sci Copenhagen Denmark ROCKWOOL Fdn Res Unit Copenhagen Denmark Johns Hopkins Univ Baltimore MD USA

ISBN: (纸本)9798891760608

Pixel-based language models process text rendered as images, which allows them to handle any script, making them a promising approach to open vocabulary language modelling. However, recent approaches use text renderers that produce a large set of almost-equivalent input patches, which may prove sub-optimal for downstream tasks, due to redundancy in the input representations. In this paper, we investigate four approaches to rendering text in the PIXEL model (Rust et al., 2023), and find that simple character bigram rendering brings improved performance on sentence-level tasks without compromising performance on token-level or multilingual tasks. This new rendering strategy also makes it possible to train a more compact model with only 22M parameters that performs on par with the original 86M parameter model. Our analyses show that character bigram rendering leads to a consistently better model but with an anisotropic patch embedding space, driven by a patch frequency bias, highlighting the connections between image patchand tokenization-based language models.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Hit the Nail on the Head: Parameter-Efficient Multi-task Tuning via Human language Intervention

Hit the Nail on the Head: Parameter-Efficient Multi-task Tun...

引用

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

作者： Lu, Wenxuan Jiang, Songhao Wang, Yijing Zang, Tianning Institute of Information Engineering Chinese Academy of Sciences Beijing China1 School of Cyber Security University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798891761681

Parameter-Efficient Fine-Tuning (PEFT) on small Pre-trained language Models (PLMs) has emerged as a promising approach to enhance their multi-tasking *** methods simultaneously train additional modules (i.e., one task-shared module and multiple task-specific modules) for adapting PLMs to downstream ***, their adaptability to new tasks is constrained, as the task-specific modules independently adapt to each task, overlooking the potential for knowledge transfer across *** this paper, we propose a novel multi-task learning framework, Inspirational Pointer (IP), that enables the transfer of prior knowledge across tasks through human language ***, we attach task descriptions to the input samples, which are then mapped to corresponding task *** on those embeddings, we adapt PLMs for downstream *** tasks share akin descriptions, allowing new task samples close to similar trained tasks in the task embedding space, hitting the memory about trained tasks of the *** experiments on the T5 model demonstrate performance improvements of our method in multi-task learning and few-shot transfer ***, we implemented the IP in decoder-only models including GPT2 and large language models (LLMs), and the results show that IP enhances the capabilities of decoder-only models. © 2024 Association for Computational Linguistics.

关键词： Decoding

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 << < 71 72 73 74 75 76 77 78 79 80 > >>

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：