检索结果-内蒙古大学图书馆

Minion: A Technology Probe for Resolving Value Conflicts through Expert-Driven and User-Driven Strategies in AI Companion Applications

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fan, Xianzhe Xiao, Qing Zhou, Xuhui Su, Yuran Lu, Zhicong Sap, Maarten Shen, Hong Tsinghua University Beijing China Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States Department of Computer Science City University of Hong Kong Hong Kong SAR China Language Technologies Institute Carnegie Mellon University PittsburghPA United States

AI companions based on large language models can role-play and converse very naturally. When value conflicts arise between the AI companion and the user, it may offend or upset the user. Yet, little research has examined such conflicts. We first conducted a formative study that analyzed 151 user complaints about conflicts with AI companions, providing design implications for our study. Based on these, we created Minion, a technology probe to help users resolve human-AI value conflicts. Minion applies a user-empowerment intervention method that provides suggestions by combining expert-driven and user-driven conflict resolution strategies. We conducted a technology probe study, creating 40 value conflict scenarios on *** and Talkie. 22 participants completed 274 tasks and successfully resolved conflicts 94.16% of the time. We summarize user responses, preferences, and needs in resolving value conflicts, and propose design implications to reduce conflicts and empower users to resolve them more effectively. Copyright © 2024, The Authors. All rights reserved.

关键词：

An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series 41

学校读者我要写书评

暂无评论

An Empirical Examination of Balancing Strategy for Counterfa...

41st International Conference on Machine Learning, ICML 2024

作者： Huang, Qiang Meng, Chuizheng Cao, Defu Huang, Biwei Chang, Yi Liu, Yan School of Artificial Intelligence Jilin University Jilin Changchun China International Center of Future Science Jilin University Jilin Changchun China Department of Computer Science University of Southern California California Los Angeles United States Halicioğlu Data Science Institute University of California San Diego San DiegoCA United States Engineering Research Center of Knowledge-Driven Human-Machine Intelligence MOE Jilin Changchun China

Counterfactual estimation from observations represents a critical endeavor in numerous application fields, such as healthcare and finance, with the primary challenge being the mitigation of treatment bias. The balancing strategy aimed at reducing covariate disparities between different treatment groups serves as a universal solution. However, when it comes to the time series data, the effectiveness of balancing strategies remains an open question, with a thorough analysis of the robustness and applicability of balancing strategies still lacking. This paper revisits counterfactual estimation in the temporal setting and provides a brief overview of recent advancements in balancing strategies. More importantly, we conduct a critical empirical examination for the effectiveness of the balancing strategies within the realm of temporal counterfactual estimation in various settings on multiple datasets. Our findings could be of significant interest to researchers and practitioners and call for a reexamination of the balancing strategy in time series settings. Copyright 2024 by the author(s)

关键词： Time series analysis

Impairments in Spatial Representations of Place Cells and Neural rhythms In APP knock-in rat model 46

学校读者我要写书评

暂无评论

Impairments in Spatial Representations of Place Cells and Ne...

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Wang, Xueling Wang, Yimeng Pang, Keliang Lu, Bai Tian, Yutao Zheng, Chenguang Fudan University Aging and Longevity Institute Institute of Biological Science Zhongshan Hospital Shanghai China Tsinghua University-Peking University Joint Center for Life Sciences Tsinghua University School of Pharmaceutical Sciences IDG/McGovern Institute for Brain Research Beijing China Tianjin University Academy of Medical Engineering and Translational Medicine Medical College Tianjin China Tianjin Key Laboratory of Brain Science and Neuroengineering Tianjin China Haihe Laboratory of Brain-Computer Interaction and Human-Machine Integration Tianjin China

ISBN: (纸本)9798350371499

Alzheimer's disease (AD) is a neurodegenerative disease that severely impacts spatial memory. Place cells in the hippocampus play an important role in spatial memory. However, neuronal activity in the hippocampus is difficult to monitor and study in human AD patients. Thus, it is critical to have an animal model that resembles closely human AD. The newly developed APPNL-G-F rat model, which is a knock-in rat line of the amyloid precursor protein (APP) with Swedish-Beyreuther/Iberian-Arctic mutations, presents a unique opportunity. In this study, we investigated how hippocampal place cells and neural rhythms were impaired in APP rats. Place cells of APP rats showed a less defined spatial tunning and disrupted remapping. In addition, APP rats exhibited decreased power of theta rhythm and slow gamma rhythm. These results suggest that the impairment of spatial memory in APP rats may be caused by the damage of place cells' ability to represent spatial location and abnormal neural rhythm in the hippocampus. © 2024 IEEE.

关键词： Rats

Real-Time Facial Expression Recognition using Facial Landmarks and Neural Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Haghpanah, Mohammad Amin Saeedizade, Ehsan Masouleh, Mehdi Tale Kalhor, Ahmad Human and Robot Interaction Lab School of Electrical and Computer Engineering University of Tehran Tehran Iran Department of Computer Science and Engineering University of Nevada Reno United States

This paper presents a lightweight algorithm for feature extraction, classification of seven different emotions, and facial expression recognition in a real-time manner based on static images of the human face. In this regard, a Multi-Layer Perceptron (MLP) neural network is trained based on the foregoing algorithm. In order to classify human faces, first, some pre-processing is applied to the input image, which can localize and cut out faces from it. In the next step, a facial landmark detection library is used, which can detect the landmarks of each face. Then, the human face is split into upper and lower faces, which enables the extraction of the desired features from each part. In the proposed model, both geometric and texture-based feature types are taken into account. After the feature extraction phase, a normalized vector of features is created. A 3-layer MLP is trained using these feature vectors, leading to 96% accuracy on the test set. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Enhanced Fine-Tuning of Lightweight Domain-Specific Q&A Model Based on Large Language Models

学校读者我要写书评

暂无评论

Enhanced Fine-Tuning of Lightweight Domain-Specific Q&A Mode...

IEEE International Conference on Software Reliability Engineering Workshops (ISSRE Wksp)

作者： Shenglin Zhang Pengtian Zhu Minghua Ma Jiagang Wang Yongqian Sun Dongwen Li Jingyu Wang Qianying Guo Xiaolei Hua Lin Zhu Dan Pei Nankai University Haihe Laboratory of Information Technology Application Innovation Microsoft Tsinghua University Tianjin Key Laboratory of Software Experience and Human Computer Interaction China Mobile Research Institute Beijing National Research Center for Information Science and Technology

ISBN: (数字)9798350367041

ISBN: (纸本)9798350367058

Large language models (LLMs) excel at general question-answering (Q&A) but often fall short in specialized domains due to a lack of domain-specific knowledge. Commercial companies face the dual challenges of privacy protection and resource constraints when involving LLMs for fine-tuning. This paper propose a novel framework, Self-Evolution, designed to address these issues by leveraging lightweight open-source LLMs through multiple iterative fine-tuning rounds. To enhance the efficiency of iterative fine-tuning, Self-Evolution employ a strategy that filters and reinforces the knowledge with higher value during the iterative process. We employed Self-Evolution on Qwen1.5-7B-Chat using 4,000 documents containing rich domain knowledge from China Mobile, achieving a performance score 174% higher on domain-specific question-answering evaluations than Qwen1.5-7B-Chat and even 22% higher than Qwen1.5-72B-Chat. Self-Evolution has been deployed in China Mobile’s daily operation and maintenance for 117 days, and it improves the efficiency of locating alarms, fixing problems, and finding related reports, with an average efficiency improvement of over 18.6%. In addition, we release Self-Evolution framework code in https://***/Zero-Pointer/Self-Evolution.

关键词： Privacy Filters Large language models Conferences Software reliability Maintenance Iterative methods Data mining Protection Faces

Benchmarks for Physical Reasoning AI

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Melnik, Andrew Schiewer, Robin Lange, Moritz Muresanu, Andrei Saeidi, Mozhgan Garg, Animesh Ritter, Helge Center for Cognitive Interaction Technology University of Bielefeld Germany Institute for Neural Computation Department of Computer Science Ruhr University Bochum Germany University of Waterloo Canada Vector Institute Canada Department of Computer Science University of Toronto Canada Department of Computer Science Stanford University United States University of Toronto Canada Georgia Institute of Technology United States

Physical reasoning is a crucial aspect in the development of general AI systems, given that human learning starts with interacting with the physical world before progressing to more complex concepts. Although researchers have studied and assessed the physical reasoning of AI approaches through various specific benchmarks, there is no comprehensive approach to evaluating and measuring progress. Therefore, we aim to offer an overview of existing benchmarks and their solution approaches and propose a unified perspective for measuring the physical reasoning capacity of AI systems. We select benchmarks that are designed to test algorithmic performance in physical reasoning tasks. While each of the selected benchmarks poses a unique challenge, their ensemble provides a comprehensive proving ground for an AI generalist agent with a measurable skill level for various physical reasoning concepts. This gives an advantage to such an ensemble of benchmarks over other holistic benchmarks that aim to simulate the real world by intertwining its complexity and many concepts. We group the presented set of physical reasoning benchmarks into subcategories so that more narrow generalist AI agents can be tested first on these groups. © 2023, CC BY.

关键词： Automobile proving grounds

Libpubl: Exploiting persistent user buffers as logs for write atomicity 21

学校读者我要写书评

暂无评论

Libpubl: Exploiting persistent user buffers as logs for writ...

13th ACM Workshop on Hot Topics In Storage and File Systems, HotStorage 2021

作者： Jung, Jaewon Choi, Jungsik Han, Hwansoo DMC Engineering Sungkyunkwan University Mobile Div. Samsung Electronics Korea Republic of Computer Science and Eng. HPC Research Center Sungkyunkwan University Korea Republic of Computer Science and Eng. Human-AI Interaction Sungkyunkwan University Korea Republic of

ISBN: (纸本)9781450385503

With recent advancement in NVM technologies, non-volatile main memory(NVMM) has been highlighted as promising systems for large scale data centers. By utilizing memory-mapped IO, researchers have attempted to provide fast IOs without kernel mode switches and complex kernel IO layers. Even though they improve the performance by taking advantage of NVMM characteristics, memory-mapped IOs still require additional user-level logging techniques to guarantee write atomicity and file system integrity. We propose a user-level library file system, Libpubl, which is designed to minimize the write amplification overhead of traditional logging by exploiting persistent user buffers as logs. Libpubl ensures atomic updates of data and improves the performance and the scalability. Compared to the state-of-the-art NVM file systems, Libpubl increases the performance by 50∼120% in Fio benchmark. © 2021 Association for Computing Machinery.

关键词： Benchmarking

Conversational Product Recommendation using LLM

学校读者我要写书评

暂无评论

Conversational Product Recommendation using LLM

Electronic Communications, Internet of Things and Big Data (ICEIB), International Conference on

作者： Ting-Jui Chang Lydia Hsiao-Mei Lin Richard Tzong-Han Tsai Department of Computer Science and Information Engineering National Central University Taoyuan Taiwan Department of Interaction Design National Taipei University of Technology Taipei Taiwan Research Center for Humanities and Social Sciences Academia Sinica Taipei Taiwan

ISBN: (数字)9798350360721

ISBN: (纸本)9798350360738

It is expected to deploy chatbots as sales assistants on e-commerce platforms soon. In recent years, the capabilities demonstrated by large language models (LLMs) indicate their suitability for this role. However, a dialogue process is not fully established. Most existing works concentrate on searching for ideal products, such as Retrieval-Augmented Generation (RAG) and product search. Many proposed methods rely on product reviews. However, in the case of some e-commerce platform products, valuable reviews are often lacking, rendering these approaches impractical. Thus, we studied how to assist users and select a set of candidate products. Accordingly, we simulated sales conversations based on the product features provided by the seller, using LLM and reliable content while addressing the cold-start problem. Specifically, we used product features to generate customer persona for user simulation. LLM was used to play the role of sales assistant in giving recommendations. The experimental results showed that practical conversation was created between customers and chatbots in Traditional Chinese. The code and results are available at: https://***/terryobe-ncu/CPR_LLM

关键词： Reviews Large language models Oral communication Chatbots Rendering (computer graphics) Question generation Safety

How Users Who are Blind or Low Vision Play Mobile Games: Perceptions, Challenges, and Strategies

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ran, Zihe Fan, Xianzhe Li, Xiyu Li, Franklin Mingzhe Lu, Zhicong Xiao, Qing Wang, Yanyun Communication University of China Beijing China Tsinghua University Beijing China Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States Department of Computer Science George Mason University FairfaxVA United States College of Media Communication and Information University of Colorado Boulder BoulderCO United States

As blind and low-vision (BLV) players engage more deeply with games, accessibility features have become essential. While some research has explored tools and strategies to enhance game accessibility, the specific experiences of these players with mobile games remain underexamined. This study addresses this gap by investigating how BLV users experience mobile games with varying accessibility levels. Through interviews with 32 experienced BLV mobile players, we explore their perceptions, challenges, and strategies for engaging with mobile games. Our findings reveal that BLV players turn to mobile games to alleviate boredom, achieve a sense of accomplishment, and build social connections, but face barriers depending on the game’s accessibility level. We also compare mobile games to other forms of gaming, highlighting the relative advantages of mobile games, such as the inherent accessibility of smartphones. This study contributes to understanding BLV mobile gaming experiences and provides insights for enhancing accessible mobile game design. Copyright © 2025, The Authors. All rights reserved.

关键词： Game design