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

14,558 篇 会议
663 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

15,362 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

11,025 篇 工学
- 10,359 篇 计算机科学与技术...
- 5,436 篇 软件工程
- 1,474 篇 信息与通信工程
- 963 篇 电气工程
- 925 篇 控制科学与工程
- 446 篇 生物工程
- 223 篇 网络空间安全
- 220 篇 化学工程与技术
- 187 篇 机械工程
- 175 篇 生物医学工程（可授...
- 144 篇 电子科学与技术（可...
- 102 篇 仪器科学与技术
- 99 篇 安全科学与工程
2,494 篇 理学
- 1,163 篇 数学
- 655 篇 物理学
- 520 篇 生物学
- 395 篇 统计学（可授理学、...
- 241 篇 系统科学
- 235 篇 化学
2,427 篇 管理学
- 1,755 篇 图书情报与档案管...
- 760 篇 管理科学与工程(可...
- 241 篇 工商管理
- 106 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
514 篇 医学
- 303 篇 临床医学
- 284 篇 基础医学(可授医学...
- 113 篇 公共卫生与预防医...
278 篇 法学
- 249 篇 社会学
238 篇 教育学
- 225 篇 教育学
100 篇 农学
98 篇 经济学
9 篇 艺术学
7 篇 哲学
4 篇 军事学

主题

3,557 篇 natural language...
1,786 篇 natural language...
953 篇 computational li...
740 篇 semantics
682 篇 machine learning
613 篇 deep learning
520 篇 natural language...
352 篇 computational mo...
343 篇 accuracy
339 篇 training
335 篇 large language m...
335 篇 sentiment analys...
325 篇 feature extracti...
312 篇 data mining
290 篇 speech processin...
260 篇 speech recogniti...
256 篇 transformers
236 篇 neural networks
218 篇 iterative method...
212 篇 support vector m...

机构

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

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
26 篇 wen ji-rong
26 篇 lapata mirella
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

14,282 篇 英文
966 篇 其他
113 篇 中文
18 篇 法文
14 篇 土耳其文
2 篇 德文
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 15363 条记录，以下是951-960 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：

Dual-Space Knowledge Distillation for Large language Models

Dual-Space Knowledge Distillation for Large Language Models

引用

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

作者： Zhang, Songming Zhang, Xue Sun, Zengkui Chen, Yufeng Xu, Jinan Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China

ISBN: (纸本)9798891761643

Knowledge distillation (KD) is known as a promising solution to compress large language models (LLMs) via transferring their knowledge to smaller *** this process, white-box KD methods usually minimize the distance between the output distributions of the two models so that more knowledge can be ***, in the current white-box KD framework, the output distributions are from the respective output spaces of the two models, using their own prediction *** argue that the space discrepancy will lead to low similarity between the teacher model and the student model on both representation and distribution ***, this discrepancy also hinders the KD process between models with different vocabularies, which is common for current *** address these issues, we propose a dual-space knowledge distillation (DSKD) framework that unifies the output spaces of the two models for *** the basis of DSKD, we further develop a cross-model attention mechanism, which can automatically align the representations of the two models with different ***, our framework is not only compatible with various distance functions for KD (e.g., KL divergence) like the current framework, but also supports KD between any two LLMs regardless of their *** on task-agnostic instruction-following benchmarks show that DSKD significantly outperforms the current white-box KD framework with various distance functions, and also surpasses existing KD methods for LLMs with different vocabularies. © 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

The Mystery of the Pathological Path-star Task for language Models

The Mystery of the Pathological Path-star Task for Language ...

引用

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

作者： Frydenlund, Arvid University of Toronto Vector Institute Canada

ISBN: (纸本)9798891761643

The recently introduced path-star task is a minimal task designed to exemplify limitations to the abilities of language models (Bachmann and Nagarajan, 2024). It involves a path-star graph where multiple arms radiate from a single starting node and each node is unique. Given the start node and a specified target node that ends an arm, the task is to generate the arm containing that target node. This is straightforward for a human but surprisingly difficult for language models, which did not outperform the random baseline. The authors hypothesized this is due to a deficiency in teacher-forcing and the next-token prediction paradigm. We demonstrate the task is learnable using teacher-forcing in alternative settings and that the issue is partially due to representation. We introduce a regularization method using structured samples of the same graph but with differing target nodes, improving results across a variety of model types. We provide RASP proofs showing the task is theoretically solvable. Finally, we find settings where an encoder-only model can consistently solve the task. © 2024 Association for Computational Linguistics.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

UniFashion: A Unified Vision-language Model for Multimodal Fashion Retrieval and Generation

UniFashion: A Unified Vision-Language Model for Multimodal F...

引用

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

作者： Zhao, Xiangyu Zhang, Yuehan Zhang, Wenlong Wu, Xiao-Ming Department of Computing The Hong Kong Polytechnic University Hong Kong Wuhan University China Shanghai AI Laboratory China

ISBN: (纸本)9798891761643

The fashion domain includes a range of real-world multimodal tasks, such as multimodal retrieval and generation. Recent advancements in AI-generated content, particularly large language models for text and diffusion models for visuals, have spurred significant research interest in applying these multimodal models to fashion. However, fashion models must also effectively handle embedding tasks, like image-to-text and text-to-image retrieval. Moreover, current unified fashion models often lack the capability for image generation. In this work, we present UniFashion, a unified framework that tackles the challenges of multimodal generation and retrieval tasks in the fashion domain, by integrating image and text generation with retrieval tasks. UniFashion unifies embedding and generative processes through the use of a diffusion model and LLM, enabling controllable and high-fidelity generation. Our model significantly outperforms previous state-of-the-art models focused on single tasks across various fashion-related challenges and can be easily adapted to manage complex vision-language tasks. This study highlights the synergistic potential between multimodal generation and retrieval, offering a promising avenue for future research in the fashion domain. The source code is available at https://***/xiangyu-mm/UniFashion. © 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

Estimating Knowledge in Large language Models Without Generating a Single Token

Estimating Knowledge in Large Language Models Without Genera...

引用

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

作者： Gottesman, Daniela Geva, Mor Blavatnik School of Computer Science Tel Aviv University Israel

ISBN: (纸本)9798891761643

To evaluate knowledge in large language models (LLMs), current methods query the model and then evaluate its generated responses. In this work, we ask whether evaluation can be done before the model has generated any text. Concretely, is it possible to estimate how knowledgeable a model is about a certain entity, only from its internal computation? We study this question with two tasks: given a subject entity, the goal is to predict (a) the ability of the model to answer common questions about the entity, and (b) the factuality of open-ended responses generated by the model about the entity. Experiments with a variety of LLMs show that KEEN, a simple probe trained over internal subject representations, succeeds at both tasks - correlating with both the QA accuracy of the model per-subject and FActScore, a recent factuality metric in open-ended generation. Moreover, KEEN naturally aligns with the model's hedging behavior and faithfully reflects changes in the model's knowledge after fine-tuning. Lastly, we show a more interpretable yet equally performant variant of KEEN, which highlights a small set of tokens indicative of clusters and gaps in the model's knowledge. Being simple and lightweight, KEEN can be leveraged to guide decisions such as when it is appropriate to apply further training or augment queries with retrieval. © 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

FIRST: Teach A Reliable Large language Model Through Efficient Trustworthy Distillation

FIRST: Teach A Reliable Large Language Model Through Efficie...

引用

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

作者： Shum, Kashun Xu, Minrui Zhang, Jianshu Chen, Zixin Diao, Shizhe Dong, Hanze Zhang, Jipeng Raza, Muhammad Omer The Hong Kong University of Science and Technology Hong Kong Wuhan University China NVIDIA United States Purdue University United States

ISBN: (纸本)9798891761643

Large language models (LLMs) have become increasingly prevalent in our daily lives, leading to an expectation for LLMs to be trustworthy - both accurate and well-calibrated (the prediction confidence should align with its ground truth correctness likelihood). Nowadays, fine-tuning has become the most popular method for adapting a model to practical usage by significantly increasing accuracy on downstream tasks. Despite the great accuracy it achieves, we found fine-tuning is still far away from satisfactory trustworthiness due to "tuning-induced mis-calibration". In this paper, we delve deeply into why and how mis-calibration exists in fine-tuned models, and how distillation can alleviate the issue. Then we further propose a brand new method named EFfIcient TRustworthy DiSTillation (FIRST), which utilizes a small portion of teacher's knowledge to obtain a reliable language model in a cost-efficient way. Specifically, we identify the "concentrated knowledge" phenomenon during distillation, which can significantly reduce the computational burden. Then we apply a "trustworthy maximization" process to optimize the utilization of this small portion of concentrated knowledge before transferring it to the student. Experimental results demonstrate the effectiveness of our method, where better accuracy (+2.3%) and less mis-calibration (- 10%) are achieved on average across both in-domain and out-of-domain scenarios, indicating better trustworthiness. © 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

Hopping Too Late: Exploring the Limitations of Large language Models on Multi-Hop Queries

Hopping Too Late: Exploring the Limitations of Large Languag...

引用

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

作者： Biran, Eden Gottesman, Daniela Yang, Sohee Geva, Mor Globerson, Amir Tel Aviv University Israel UCL United States Google Research United States

ISBN: (纸本)9798891761643

Large language models (LLMs) can solve complex multi-step problems, but little is known about how these computations are implemented internally. Motivated by this, we study how LLMs answer multi-hop queries such as "The spouse of the performer of Imagine is". These queries require two information extraction steps: a latent one for resolving the first hop ("the performer of Imagine") into the bridge entity (John Lennon), and another for resolving the second hop ("the spouse of John Lennon") into the target entity (Yoko Ono). Understanding how the latent step is computed internally is key to understanding the overall computation. By carefully analyzing the internal computations of transformer-based LLMs, we discover that the bridge entity is resolved in the early layers of the model. Then, only after this resolution, the two-hop query is solved in the later layers. Because the second hop commences in later layers, there could be cases where these layers no longer encode the necessary knowledge for correctly predicting the answer. Motivated by this, we propose a novel "back-patching" analysis method whereby a hidden representation from a later layer is patched back to an earlier layer. We find that in up to 66% of previously incorrect cases there exists a back-patch that results in the correct generation of the answer, showing that the later layers indeed sometimes lack the needed functionality. Overall, our methods and findings open further opportunities for understanding and improving latent reasoning in transformer-based LLMs. © 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

Learn to Refuse: Making Large language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism

Learn to Refuse: Making Large Language Models More Controlla...

引用

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

作者： Cao, Lang University of Illinois Department of Computer Science Urbana-Champaign United States

ISBN: (纸本)9798891761643

Large language models (LLMs) have demonstrated impressive language understanding and generation capabilities, enabling them to answer a wide range of questions across various domains. However, these models are not flawless and often produce responses that contain errors or misinformation. These inaccuracies, commonly referred to as hallucinations, render LLMs unreliable and even unusable in many scenarios. In this paper, our focus is on mitigating the issue of hallucination in LLMs, particularly in the context of question-answering. Instead of attempting to answer all questions, we explore a refusal mechanism that instructs LLMs to refuse to answer challenging questions in order to avoid errors. We then propose a simple yet effective solution called Learn to Refuse (L2R), which incorporates the refusal mechanism to enable LLMs to recognize and refuse to answer questions that they find difficult to address. To achieve this, we utilize a structured knowledge base to represent all the LLM's understanding of the world, enabling it to provide traceable gold knowledge. This knowledge base is separate from the LLM and initially empty. It can be filled with validated knowledge and progressively expanded. When an LLM encounters questions outside its domain, the system recognizes its knowledge scope and determines whether it can answer the question independently. Additionally, we introduce a method for automatically and efficiently expanding the knowledge base of LLMs. Through qualitative and quantitative analysis, we demonstrate that our approach enhances the controllability and reliability of LLMs. © 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

VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-language Models Alignment

VLFeedback: A Large-Scale AI Feedback Dataset for Large Visi...

引用

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

作者： Li, Lei Xie, Zhihui Li, Mukai Chen, Shunian Wang, Peiyi Chen, Liang Yang, Yazheng Wang, Benyou Kong, Lingpeng Liu, Qi The University of Hong Kong Hong Kong Peking University China The Chinese University of HongKong Shenzhen China

ISBN: (纸本)9798891761643

As large vision-language models (LVLMs) evolve rapidly, the demand for high-quality and diverse data to align these models becomes increasingly crucial. However, the creation of such data with human supervision proves costly and time-intensive. In this paper, we investigate the efficacy of AI feedback to scale supervision for aligning LVLMs. We introduce VLFeedback, the first large-scale vision-language feedback dataset, comprising over 82K multi-modal instructions and comprehensive rationales generated by off-the-shelf models without human annotations. To evaluate the effectiveness of AI feedback for vision-language alignment, we train Silkie, an LVLM fine-tuned via direct preference optimization on VLFeedback. Silkie showcases exceptional performance regarding helpfulness, visual faithfulness, and safety metrics. It outperforms its base model by 6.9% and 9.5% in perception and cognition tasks, reduces hallucination issues on MMHal-Bench, and exhibits enhanced resilience against red-teaming attacks. Furthermore, our analysis underscores the advantage of AI feedback, particularly in fostering preference diversity to deliver more comprehensive improvements. Our dataset, training code and models are available at https://***. © 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

If CLIP Could Talk: Understanding Vision-language Model Representations Through Their Preferred Concept Descriptions

If CLIP Could Talk: Understanding Vision-Language Model Repr...

引用

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

作者： Esfandiarpoor, Reza Menghini, Cristina Bach, Stephen H. Department of Computer Science Brown University United States Data Science Institute Brown University United States

ISBN: (纸本)9798891761643

Recent works often assume that Vision-language Model (VLM) representations are based on visual attributes like shape. However, it is unclear to what extent VLMs prioritize this information to represent concepts. We propose Extract and Explore (EX2), a novel approach to characterize textual features that are important for VLMs. EX2 uses reinforcement learning to align a large language model with VLM preferences and generates descriptions that incorporate features that are important for the VLM. Then, we inspect the descriptions to identify features that contribute to VLM representations. Using EX2, we find that spurious descriptions have a major role in VLM representations despite providing no helpful information, e.g., Click to enlarge photo of CONCEPT. More importantly, among informative descriptions, VLMs rely significantly on non-visual attributes like habitat (e.g., North America) to represent visual concepts. Also, our analysis reveals that different VLMs prioritize different attributes in their representations. Overall, we show that VLMs do not simply match images to scene descriptions and that non-visual or even spurious descriptions significantly influence their representations. Code: https://***/BatsResearch/ex2. © 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

ActPlan-1K: Benchmarking the Procedural Planning Ability of Visual language Models in Household Activities

ActPlan-1K: Benchmarking the Procedural Planning Ability of ...

引用

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

作者： Su, Ying Ling, Zhan Shi, Haochen Cheng, Jiayang Yim, Yauwai Song, Yangqiu HKUST Hong Kong University of California San Diego United States

ISBN: (纸本)9798891761643

Large language models (LLMs) have been adopted to process textual task description and accomplish procedural planning in embodied AI tasks because of their powerful reasoning ability. However, there is still lack of study on how vision language models (VLMs) behave when multi-modal task inputs are considered. Counterfactual planning that evaluates the model's reasoning ability over alternative task situations are also under exploited. In order to evaluate the planning ability of both multimodal and counterfactual aspects, we propose ActPlan-1K. ActPlan-1K is a multi-modal planning benchmark constructed based on ChatGPT and household activity simulator iGibson2. The benchmark consists of 153 activities and 1,187 instances. Each instance describing one activity has a natural language task description and multiple environment images from the simulator. The gold plan of each instance is action sequences over the objects in provided scenes. Both the correctness and commonsense satisfaction are evaluated on typical VLMs. It turns out that current VLMs are still struggling at generating human-level procedural plans for both normal activities and counterfactual activities. We further provide automatic evaluation metrics by finetuning over BLEURT model to facilitate future research on our benchmark. © 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

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 << < 92 93 94 95 96 97 98 99 100 101 > >>

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：