We attempted to prompt a GPT system to generate a response to a specific prompt and detail the steps the system followed to produce the generated response. For this purpose, we employed the open-source toolkit Gpt4all...
详细信息
ISBN:
(数字)9783031574023
ISBN:
(纸本)9783031574016;9783031574023
We attempted to prompt a GPT system to generate a response to a specific prompt and detail the steps the system followed to produce the generated response. For this purpose, we employed the open-source toolkit Gpt4all, utilizing the opensource language model LLama 7bit-quantized. The pretrained model was specialized on a series of thematic texts using the open-source libraries Langchain. The choice of toolkit, model, and libraries was determined by two factors: 1) the intention to utilize both fully open-source toolkits and models, and 2) the necessity to use toolkits and models capable of running on consumer-grade CPUs, within our available resources. This work focuses on the concepts of prediction, bias, and explainability that motivated the aforementioned experiment.
We describe the early stages of Artificial Intelligence (AI) research and future robotic development projects to study how and why to integrate Large Language Model (LLM) Generative AI (LLM-GAI) into educational softw...
详细信息
ISBN:
(纸本)9789819744411;9789819744428
We describe the early stages of Artificial Intelligence (AI) research and future robotic development projects to study how and why to integrate Large Language Model (LLM) Generative AI (LLM-GAI) into educational software systems we have built during the past decade. Our current focus has been to study what we do not know about a variety of Natural Language Processing (NLP) tasks across a range of educational settings within the United States. As a prelude to large-scale research and writing grant proposals, we conducted thought experiments (often known as Gedanken experiments) to identify factors shaping the effective usage of LLM-GAI within inclusive-adaptive teaching-learning environments. While qualitative and non-experimental, we wanted to delineate the scope of problem areas to refine a model of an inclusive-adaptive-learning environment we have been developing during the past three years.
Blockchain systems often rely on rationality assumptions for their security, expecting that nodes are motivated to maximize their profits. These systems thus design their protocols to incentivize nodes to execute the ...
详细信息
ISBN:
(纸本)9783031488054;9783031488061
Blockchain systems often rely on rationality assumptions for their security, expecting that nodes are motivated to maximize their profits. These systems thus design their protocols to incentivize nodes to execute the honest protocol but fail to consider out-of-band collusion. Existing works analyzing rationality assumptions are limited in their scope, either by focusing on a specific protocol or relying on nonexisting financial instruments. We propose a general rational attack on rationality by leveraging an external channel that incentivizes nodes to collude against the honest protocol. Our approach involves an attacker creating an out-of-band bribery smart contract to motivate nodes to double-spend their transactions in exchange for shares in the attacker's profits. We provide a game theory model to prove that any rational node is incentivized to follow the malicious protocol. We discuss our approach to attacking the Bitcoin and Ethereum blockchains, demonstrating that irrational behavior can be rational in real-world blockchain systems when analyzing rationality in a larger ecosystem. We conclude that rational assumptions only appear to make the system more secure and offer a false sense of security under the flawed analysis.
The traditional street-level bureaucrat's (SLB's) role has undergone significant changes in the age of digital transformation. These changes have challenged Lipsky's description of the SLB. To address this...
详细信息
ISBN:
(纸本)9783031702730;9783031702747
The traditional street-level bureaucrat's (SLB's) role has undergone significant changes in the age of digital transformation. These changes have challenged Lipsky's description of the SLB. To address this, our study aims to analyze how the ongoing digital transformation influences the role of traditional SLB's, their work activities, and organization. The research question we ask is: How does digital transformation in the public sector influence the roles and work activities of traditional street-level bureaucrats? We have analyzed three large government agencies that administer public services in Scandinavia. We applied Nograsek & Vintar's framework as a sociotechnical analytical lens in our exploratory qualitative study of three large public organizations. Focusing people, work activities and processes, and enabling digital technologies, we have identified five bureaucratic roles: (1) The automated bureaucrat, (2) the self-servicing citizen, (3) the front-office employee, (4) the back-office employee, and (5) the specialized bureaucrat. While the SLB was an essential actor in the traditional street-level bureaucracy, these five roles are equally essential to a functioning contemporary bureaucracy. We argue that the five roles have greater explanatory power for understanding bureaucratic roles, including digital technologies, and contemporary ways of managing public services in the age of digital transformation.
Various advanced tools and technologies have had a significant impact on the practice and education of translation. In this era of AI, the emergence of generative technology has introduced an advanced conversational w...
详细信息
ISBN:
(纸本)9789819742424;9789819742431
Various advanced tools and technologies have had a significant impact on the practice and education of translation. In this era of AI, the emergence of generative technology has introduced an advanced conversational work mode that involves closer coordination between humans and machines. ChatGPT, as a representative of generative AI technology, holds significant potential for further advancements in the field of translation. Against this background, this study aims to investigate the utilization of this new generative AI technology in the context of translation education. As an invaluable resource for translation students, ChatGPT can offer them valuable guidance and support throughout the translation task. The article first explores how ChatGPT can effectively aid translation learners at different phases of the translation process, encompassing pre-translation, machine translation, and post-editing stages. Then, drawing on the influential PACTE model of translation competence, it explicates how ChatGPT can contribute to the enhancement of translation students' competence, particularly their bilingual, extra-linguistic, and strategic sub-competences.
Many museums and libraries conducted efforts to digitize their assets, and many historic documents are now available as digital images. However, these documents are not directly accessible to retrieval systems that re...
详细信息
ISBN:
(纸本)9783031724398;9783031724404
Many museums and libraries conducted efforts to digitize their assets, and many historic documents are now available as digital images. However, these documents are not directly accessible to retrieval systems that rely on written text and not images. In this study, the novel GPT4-Vision is being studied for its ability of optical character recognition (OCR), in cases where established methods, such as Tesseract may have difficulties. We find that GPT4-Vision provides excellent results even in cases where even humans struggle. We also identified a number of key limitations, including the long runtime implying high energy requirements, the lack of handling of rotated images, the necessity for layout hints, and limitations regarding image size. Even with these limitations, it is expected that large language models and vision transformers will play an important role to make historical documents more accessible for further processing, or directly to users.
This paper addresses the lack of Ukrainian representation in digital epigraphy by developing a standardised vocabulary for Ukrainian inscriptions(1). While existing projects like the electronic archive of Greek and La...
详细信息
ISBN:
(纸本)9783031724398;9783031724404
This paper addresses the lack of Ukrainian representation in digital epigraphy by developing a standardised vocabulary for Ukrainian inscriptions(1). While existing projects like the electronic archive of Greek and Latin epigraphy (EAGLE) have comprehensive vocabularies for Greco-Roman artifacts, Ukrainian remains absent. By expanding the EAGLE vocabulary, we propose integrating Ukrainian terms into the framework. We also build a named entity recognition (NER) corpus for Ukrainian epigraphic inscriptions, train specialised NER models, and apply them to a larger corpus to discover new terms. This first step in building this vocabulary will further enable cross-lingual referencing of Ukrainian epigraphic data, enriching the digital humanities (DH) landscape while fostering broader academic collaboration and resource sharing.1An example is presented Fig. 1.
In formal work on the meaning of English, intonation with expressive, or (allegedly) emotive, meaning has received little attention, and has been treated as separate from compositional meaning. I argue against this ba...
详细信息
ISBN:
(数字)9783031608780
ISBN:
(纸本)9783031608773;9783031608780
In formal work on the meaning of English, intonation with expressive, or (allegedly) emotive, meaning has received little attention, and has been treated as separate from compositional meaning. I argue against this based on data from Japanese, showing that expressive intonation can be part of compositional meaning, hence "grammatical". Focusing on intonation patterns occurring with the Japanese sentence-final particle yo, I propose a compositional analysis of its non-emotive meaning and argue that English intonation carries the same complex meaning-thus, it is within the scope of formal semantics/pragmatics.
The traditional 'teacher-centered' indoctrination model of music education reduces children's enjoyment of learning music. Preschool children are naturally curious, energetic, and have short attention span...
详细信息
ISBN:
(纸本)9783031610462;9783031610479
The traditional 'teacher-centered' indoctrination model of music education reduces children's enjoyment of learning music. Preschool children are naturally curious, energetic, and have short attention spans, making it difficult to explore traditional music. This teaching model is increasingly unsuitable for the needs of contemporary enlightenment education. This study is based on the actual implementation of the "MR Music Classroom" project, using mixed reality (MR) technology to draw inspiration from traditional Chinese children's stories and transform them into Visually rich content. Virtual teaching content and real space are superimposed on children for learning and interaction. The modular 25-min music teaching process is both educational and entertaining, providing preschool children with an overall experience in visual, tactile, and interactive dimensions. In the context of integrating MR into introductory music education, the project feasibility assessment included evaluating typical examples of complex MR system environments and measuring the popularity of the Music Magic Classroom. This move is intended to demonstrate the feasibility of the project. The results of this research have certain reference value for the application of MR teaching model and user interface interaction in educational environments. Words.
When analyzing interactions during collaborative problem solving (CPS) tasks, many different communication modalities are likely to be present and interpretable. These modalities may include speech, gesture, action, a...
详细信息
ISBN:
(纸本)9783031601064;9783031601071
When analyzing interactions during collaborative problem solving (CPS) tasks, many different communication modalities are likely to be present and interpretable. These modalities may include speech, gesture, action, affect, pose and object position in physical space, amongst others. As AI becomes more prominent in day-to-day use and various learning environments, such as classrooms, there is potential for it to support additional understanding into how small groups work together to complete CPS tasks. Designing interactive AI to support CPS requires creating a system that supports multiple different modalities. In this paper we discuss the importance of multimodal features to modeling CPS, how different modal channels must interact in a multimodal AI agent that supports a wide range of tasks, and design considerations that require forethought when building such a system that most effectively interacts with and aids small groups in successfully completing CPS tasks. We also outline various tool sets that can be leveraged to support each of the individual features and their integration, and various applications for such a system.
暂无评论