检索结果-内蒙古大学图书馆

On the Robustness of Editing Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Xinbei Ju, Tianjie Qiu, Jiyang Zhang, Zhuosheng Zhao, Hai Liu, Lifeng Wang, Yulong School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China Baichuan Intelligent Technology China

Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. Model editing enables the manipulation of specific knowledge memories and the behavior of language generation without retraining. However, the robustness of model editing remains an open question. This work seeks to understand the strengths and limitations of editing methods, facilitating practical applications of communicative AI. We focus on three key research questions. RQ1: Can edited LLMs behave consistently resembling communicative AI in realistic situations? RQ2: To what extent does the rephrasing of prompts lead LLMs to deviate from the edited knowledge memory? RQ3: Which knowledge features are correlated with the performance and robustness of editing? Our empirical studies uncover a substantial disparity between existing editing methods and the practical application of LLMs. On rephrased prompts that are flexible but common in realistic applications, the performance of editing experiences a significant decline. Further analysis shows that more popular knowledge is memorized better, easier to recall, and more challenging to edit effectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational linguistics

Multi-turn Dialogue Comprehension from a Topic-aware Perspective

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ma, Xinbei Xu, Yi Zhao, Hai Zhang, Zhuosheng The Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

Dialogue related Machine Reading Comprehension requires language models to effectively decoupling and modeling on multi-turn dialogue passages. As a dialogue development goes after the intentions of participants, its topic may not keep constant through the whole passage. Hence, it is non-trivial to detect and leverage the topic shift in dialogue modeling. Topic modeling, although has been widely studied in plain text, deserves far more utilization in dialogue reading comprehension. This paper proposes to model multi-turn dialogues from a topic-aware perspective. We start with a dialogue segmentation algorithm to split a dialogue passage into topic-concentrated fragments in an unsupervised way. Then we use these fragments as topic-aware language processing units in further dialogue comprehension. On one hand, the split segments indict specific topic rather than mixed intention, thus show convenient on in-domain topic detection and location. For this task, we design a clustering system with a self-training auto-encoder, and we build two constructed datasets for evaluation. On the other hand, the split segments are appropriate element of multi-turn dialogue response selection. For this purpose, we further present a novel model, Topic-Aware Dual-Attention Matching (TADAM) Network, which takes topic segments as processing element and matches response candidates with a dual cross-attention. Empirical studies on three public benchmarks show great improvements over baselines. Our work continues the previous studies on document topic, and brings the dialogue modeling to a novel topic-aware perspective with exhaustive experiments and analyses. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

Federated semi-supervised medical image classification via inter-client relation matching

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Quande Yang, Hongzheng Dou, Qi Heng, Pheng-Ann Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Department of Computer Science and Engineering Beihang University China Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

Federated learning (FL) has emerged with increasing popularity to collaborate distributed medical institutions for training deep networks. However, despite existing FL algorithms only allow the supervised training setting, most hospitals in realistic usually cannot afford the intricate data labeling due to absence of budget or expertise. This paper studies a practical yet challenging FL problem, named Federated Semi-supervised Learning (FSSL), which aims to learn a federated model by jointly utilizing the data from both labeled and unlabeled clients (i.e., hospitals). We present a novel approach for this problem, which improves over traditional consistency regularization mechanism with a new inter-client relation matching scheme. The proposed learning scheme explicitly connects the learning across labeled and unlabeled clients by aligning their extracted disease relationships, thereby mitigating the deficiency of task knowledge at unlabeled clients and promoting discriminative information from unlabeled samples. We validate our method on two large-scale medical image classification datasets. The effectiveness of our method has been demonstrated with the clear improvements over state-of-the-arts as well as the thorough ablation analysis on both tasks4 © 2021, CC BY-NC-ND.

关键词： Hospitals

DISCOVID: discovering patterns of COVID-19 infection from recovered patients: a case study in Saudi Arabia

学校读者我要写书评

暂无评论

International Journal of Information Technology (Singapore) 2022年第6期14卷 2825-2838页

作者： Alafif, Tarik Etaiwi, Alaa Hawsawi, Yousef Alrefaei, Abdulmajeed Albassam, Ayman Althobaiti, Hassan Computer Science Department Jamoum University College Umm Al-Qura University Makkah Jamoum 25375 Saudi Arabia Pathology and laboratory medicine Department King Faisal Specialist Hospital and Research Center Makkah Jeddah 21499 Saudi Arabia Saudi Human Genome program-Jeddah Satellite Laboratory Research Center King Faisal Specialist Hospital and Research Center Makkah Jeddah 21499 Saudi Arabia Biology Department Umm Al-Qura University Makkah Jamoum 25375 Saudi Arabia

A respiratory syndrome COVID-19 pandemic has become a serious global concern. Still, a large number of people have been daily infected worldwide. Discovering COVID-19 infection patterns is significant for health providers towards understanding the infection factors. Current COVID-19 research works have not been attempted to discover the infection patterns, yet. In this paper, we employ an Association Rules Apriori (ARA) algorithm to discover the infection patterns from COVID-19 recovered patients’ data. A non-clinical COVID-19 dataset is introduced and analyzed. A sample of recovered patients’ data is manually collected in Saudi Arabia. Our manual computation and experimental results show strong associative rules with high confidence scores among males, weight above 70 kilograms, height above 160 centimeters, and fever patterns. These patterns are the strongest infection patterns discovered from COVID-19 recovered patients’ data. © 2022, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Association rules apriori algorithm COVID-19 Infection patterns

Cloudless Skies? Decentralizing Mobile interaction 20

学校读者我要写书评

暂无评论

Cloudless Skies? Decentralizing Mobile Interaction

22nd International Conference on human-computer interaction with Mobile Devices and Services

作者： Britta Schulte Sujay Shalawadi Max Van Kleek Florian Echtler Human-Computer Interaction Bauhaus-University Weimar Germany Bauhaus Universität Germany Department of Computer Science University of Oxford United Kingdom HCC Group Aalborg University Denmark

ISBN: (纸本)9781450380522

Mobile interaction is now almost exclusively dependent on an intransparent cloud infrastructure beyond the users’ control, resulting in multiple issues related to security, privacy, and availability. While alternative approaches based on decentralized network architectures exist, these have their own set of issues such as lack of usability or content moderation. In this workshop, we bring together researchers from related, but rarely interconnected fields to discuss issues and opportunities related to decentralization. We will develop and discuss current and future scenarios for decentralized mobile interaction, both utopian and dystopian. We invite researchers interested in implementation and networking aspects of mobile decentralization as well as those focusing on ethical, legal and social implications (ELSI) of these alternative approaches to the mobile ecosystem.

关键词： social aspects of computing peer-to-peer networks mobile computing decentralization cloud services ELSI

EmoBench: Evaluating the Emotional Intelligence of Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sabour, Sahand Liu, Siyang Zhang, Zheyuan Liu, June M. Zhou, Jinfeng Sunaryo, Alvionna S. Li, Juanzi Lee, Tatia M.C. Mihalcea, Rada Huang, Minlie The CoAI Group DCST Institute for Artificial Intelligence Tsinghua University Beijing China The LIT Group Department of Computer Science and Engineering University of Michigan Ann Arbor United States DCST Tsinghua University Beijing China The Laboratory of Neuropsychology and Human Neuroscience HKU Hong Kong

Recent advances in Large Language Models (LLMs) have highlighted the need for robust, comprehensive, and challenging benchmarks. Yet, research on evaluating their Emotional Intelligence (EI) is considerably limited. Existing benchmarks have two major shortcomings: first, they mainly focus on emotion recognition, neglecting essential EI capabilities such as emotion regulation and thought facilitation through emotion understanding;second, they are primarily constructed from existing datasets, which include frequent patterns, explicit information, and annotation errors, leading to unreliable evaluation. We propose EMOBENCH, a benchmark that draws upon established psychological theories and proposes a comprehensive definition for machine EI, including Emotional Understanding and Emotional Application. EMOBENCH includes a set of 400 hand-crafted questions in English and Chinese, which are meticulously designed to require thorough reasoning and understanding. Our findings reveal a considerable gap between the EI of existing LLMs and the average human, highlighting a promising direction for future research. Our code and data are publicly available at https://***/Sahandfer/EmoBench. © 2024, CC BY.

关键词： Emotional intelligence

Bidirectional human-AI Alignment: Emerging Challenges and Opportunities

学校读者我要写书评

暂无评论

Bidirectional Human-AI Alignment: Emerging Challenges and Op...

2025 CHI Conference on human Factors in Computing Systems, CHI EA 2025

作者： Shen, Hua Knearem, Tiffany Ghosh, Reshmi Liu, Michael Xieyang Monroy-Hernández, Andrés Wu, Tongshuang Yang, Diyi Huang, Yun Mitra, Tanushree Li, Yang Hearst, Marti The Information School University of Washington SeattleWA United States Google San FranciscoCA United States Microsoft Corp Microsoft AI Development Acceleration Program CambridgeMA United States Google DeepMind PittsburghPA United States Princeton University PrincetonNJ United States Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States Computer Science Department Stanford University StanfordCA United States School of Information Sciences University of Illinois at Urbana-Champaign ChampaignIL United States University of Washington SeattleWA United States Google Research Mountain ViewCA United States UC Berkeley BerkeleyCA United States

ISBN: (纸本)9798400713958

Recent advancements in general-purpose AI have highlighted the urgent need to align AI systems with the goals, ethical principles, and values of individuals and society. Existing alignment research has been primarily approached as an AI-centered, static, and unidirectional process. However, this unidirectional perspective falls short of taking into account the dynamic and evolving interaction between humans and AI, necessitating a shift toward a bidirectional, interconnected mode of human-AI alignment. This SIG aims to outline the emerging areas of bidirectinoal human-AI alignment research, propose a blueprint of future goals and challenges for fundamental alignment research, and establish a shared platform to bring together experts from HCI, AI, social sciences, and more to advance interdisciplinary research and collaboration on human-AI alignment. © 2025 Copyright held by the owner/author(s).

关键词： Sociology

Channel-aware Decoupling Network for Multi-turn Dialogue Comprehension

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Zhuosheng Zhao, Hai Liu, Longxiang The Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China China

Training machines to understand natural language and interact with humans is one of the major goals of artificial intelligence. Recent years have witnessed an evolution from matching networks to pre-trained language models (PrLMs). In contrast to the plain-text modeling as the focus of the PrLMs, dialogue texts involve multiple speakers and reflect special characteristics such as topic transitions and structure dependencies between distant utterances. However, the related PrLM models commonly represent dialogues sequentially by processing the pairwise dialogue history as a whole. Thus the hierarchical information on either utterance interrelation or speaker roles coupled in such representations is not well addressed. In this work, we propose compositional learning for holistic interaction across the utterances beyond the sequential contextualization from PrLMs, in order to capture the utterance-aware and speaker-aware representations entailed in a dialogue history. We decouple the contextualized word representations by masking mechanisms in Transformer-based PrLM, making each word only focus on the words in current utterance, other utterances, and two speaker roles (i.e., utterances of sender and utterances of the receiver), respectively. In addition, we employ domain-adaptive training strategies to help the model adapt to the dialogue domains. Experimental results show that our method substantially boosts the strong PrLM baselines in four public benchmark datasets, achieving new state-of-the-art performance over previous methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

Textessence: A tool for interactive analysis of semantic shifts between corpora

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Newman-Griffis, Denis Sivaraman, Venkatesh Perer, Adam Fosler-Lussier, Eric Hochheiser, Harry Department of Biomedical Informatics University of Pittsburgh United States Human-Computer Interaction Institute Carnegie Mellon University United States Department of Computer Science and Engineering Ohio State University United States

Embeddings of words and concepts capture syntactic and semantic regularities of language;however, they have seen limited use as tools to study characteristics of different corpora and how they relate to one another. We introduce TextEssence, an interactive system designed to enable comparative analysis of corpora using embeddings. TextEssence includes visual, neighbor-based, and similarity-based modes of embedding analysis in a lightweight, web-based interface. We further propose a new measure of embedding confidence based on nearest neighborhood overlap, to assist in identifying high-quality embeddings for corpus analysis. A case study on COVID-19 scientific literature illustrates the utility of the system. TextEssence is available from https://***/drgriffis/text-essence. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings