Search results

In the era of big data, various industries are generating large amounts of text data every day. Simplifying and summarizing these data can effectively serve users and improve efficiency. Recently, zero-shot prompting in large language models (LLMs) has demonstrated remarkable performance on various language tasks. However, generating a very “concise” multi-document summary is a difficult task for it. When conciseness is specified in the zero-shot prompting, the generated multi-document summary still contains some unimportant information, even with the few-shot prompting. This paper aims to propose a LLMs prompting for multi-document summarization task.

To overcome this challenge, the authors propose chain-of-event (CoE) prompting for multi-document summarization (MDS) task. In this prompting, the authors take events as the center and propose a four-step summary reasoning process: specific event extraction; event abstraction and generalization; common event statistics; and summary generation. To further improve the performance of LLMs, the authors extend CoE prompting with the example of summary reasoning.

Summaries generated by CoE prompting are more abstractive, concise and accurate. The authors evaluate the authors’ proposed prompting on two data sets. The experimental results over ChatGLM2-6b show that the authors’ proposed CoE prompting consistently outperforms other typical promptings across all data sets.

This paper proposes CoE prompting to solve MDS tasks by the LLMs. CoE prompting can not only identify the key events but also ensure the conciseness of the summary. By this method, users can access the most relevant and important information quickly, improving their decision-making processes.

The purpose of this study was to comprehend the adoption of artificial intelligence (AI) technology-driven natural large language model (LLM)-based chatbots by customers.

A qualitative research study method was conducted. This was to explore managerial perspectives towards consumer centric technology adoption of AI plus LLM-based chatbots. This was specifically for AI-driven natural LLM-based chatbots services. The author conducted conducted in-depth personal interviews with 32 experts of digital content AI + LLM chatbot services. Thematic content analysis was undertaken to analyse the data.

The advent of natural language processing tools driven by AI technology chatbots has altered human-firm interaction. The research findings indicated that the push-pull-mooring (PPM) factors captured the phenomenon in the most comprehensive way. A total of 15 key factors influencing the adoption of AI technology-driven natural LLM-based chatbots by customers during firm customer interaction were identified in this study by the author. The thematic content analysis unraveled insights regarding transformed consumer adoptions towards AI-driven LLM-based chatbots by means of the PPM framework factors.

The empirical research investigation contributed to the literature on the PPM theoretical framework. This was specifically in the context of adoption of AI technology-driven natural LLM-based chatbots by customers during firm customer interaction.

The research study insights would help managers to restructure and reconfigure their organizational processes. This would neccessiated a shift in firm-customer interactions as demanded because of the availability of AI technology-driven natural LLM-based chatbots by customers.

This research study was based upon the PPM theoretical framework. This study provided a unique analysis of the altered firm customer interaction needs and requirements. This was one of the first studies that applied the framework of PPM theory regarding the adoption of AI technology-driven natural LLM-based chatbots by customers.

This paper focuses on image-to-text manuscript processing through Handwritten Text Recognition (HTR), a Machine Learning (ML) approach enabled by Artificial Intelligence (AI). With HTR now achieving high levels of accuracy, we consider its potential impact on our near-future information environment and knowledge of the past.

In undertaking a more constructivist analysis, we identified gaps in the current literature through a Grounded Theory Method (GTM). This guided an iterative process of concept mapping through writing sprints in workshop settings. We identified, explored and confirmed themes through group discussion and a further interrogation of relevant literature, until reaching saturation.

Catalogued as part of our GTM, 120 published texts underpin this paper. We found that HTR facilitates accurate transcription and dataset cleaning, while facilitating access to a variety of historical material. HTR contributes to a virtuous cycle of dataset production and can inform the development of online cataloguing. However, current limitations include dependency on digitisation pipelines, potential archival history omission and entrenchment of bias. We also cite near-future HTR considerations. These include encouraging open access, integrating advanced AI processes and metadata extraction; legal and moral issues surrounding copyright and data ethics; crediting individuals’ transcription contributions and HTR’s environmental costs.

Our research produces a set of best practice recommendations for researchers, data providers and memory institutions, surrounding HTR use. This forms an initial, though not comprehensive, blueprint for directing future HTR research. In pursuing this, the narrative that HTR’s speed and efficiency will simply transform scholarship in archives is deconstructed.

The purpose of this column is to inform librarians and other information professionals about prompt engineering (PE) and to challenge them to consider how it relates to the work that they are doing and consider if it might enhance their current ability to serve users.

PE is a new job category in the fields of technology and artificial intelligence. Prompt engineers use various approaches to elicit the best possible outputs from large language module technologies such as ChatGPT. This column examines the various elements present in effective prompts and how the skills, knowledge and abilities relate to the work that librarians already do, where there are disruptions and how the field of library and information science may approach studying the emergence and effectiveness of PE in resolving information needs.

While PE shares many of the goals, procedures and skillsets that librarians already know and use, it is a disruption in information-seeking processes. It is a highly complex undertaking that requires a mix of knowledge, skills and abilities. If done well, PE will allow information seekers to achieve a whole new level of results both in terms of the information retrieved and the content that is produced based on that information.

Librarians are currently generally not considered to be prime candidates for PE positions. However, this column introduces the idea that many librarians already have the knowledge, skills, abilities and aptitude to do PE. This may be as prompt engineers or by integrating PE into their existing professional practice.

The purpose of this paper is to share findings from empirically driven conceptual research into the implications for English teachers of understanding generative AI as a “tool” for writing.

The paper reports early findings from an Australian National Survey of English teachers and interrogates the notion of the AI writer as “tool” through intersectional feminist discursive-material analysis of the metaphorical entailments of the term.

Through this work, the authors have developed the concept of “coloniser tool-thinking” and juxtaposed it with First Nations and feminist understandings of “tools” and “objects” to demonstrate risks to the pursuit of social and planetary justice through understanding generative AI as a tool for English teachers and students.

Bringing together white and First Nations English researchers in dialogue, the paper contributes a unique perspective to challenge widespread and common-sense use of “tool” for generative AI services.

Since the introduction of the outstanding web AI chat system, ChatGPT, it has caused a significant impact in both academia and the business world. Many studies have started to explore its potential applications in various fields. However, there is a lack of research from the perspective of user experience. To fill this theoretical gap and provide a theoretical basis for the operation and design of related services, this study plans to develop a set of evaluation scales for AI chat system user experience and explore the relationship between various factors and user satisfaction.

This study obtained 41 evaluation indicators through literature review and user research. Subsequently, these indicators were used as questionnaire items, combined with satisfaction metrics. A total of 515 questionnaires were distributed, and factor analysis and linear regression were employed to determine the specific elements influencing user experience and the user satisfaction model.

This study found that the factors influencing user experience are usefulness, accuracy, logical inference, interactivity, growth, anthropomorphism, convenience, credibility, ease of use, creativity, and security. Among these factors, only accuracy, anthropomorphism, creativity, and security indirectly influence satisfaction through usefulness, while the rest of the factors have a direct positive impact on user satisfaction.

This study provides constructive suggestions for the design and operation of related services and serves as a reference for future theoretical research in this area.

This study offers an in-depth examination of Google Bard, an advanced artificial intelligence chatbot created by Google, focusing specifically on its potential impact on academic research. This discussion aims to comprehensively explore the features of Google Bard, highlighting its capabilities in data management, facilitating collaborative discussions, and enhancing accessibility to complex research. In addition to the aforementioned positive characteristics, we will also delve into the limitations and ethical considerations associated with this innovative device. The functionality of the system is constrained by the limitations imposed by its pre-established algorithms and training data. In addition, there are significant concerns regarding data privacy, potential biases in its responses stemming from its training data, and the wider societal implications associated with a heavy reliance on machine-generated content. Ensuring responsible and ethical utilization of Bard necessitates Google's provision of transparent communication regarding its development process. In light of the prominent functionalities demonstrated by Google Bard, it is imperative for researchers to engage in a rigorous examination of the information it presents, thereby safeguarding against the inadvertent propagation of misinformation or biased viewpoints. This will lay the groundwork for its effective integration into the academic research methodology.

This paper aims to present a lesson that showcases how artificial intelligence (AI) tools may be chiefly used in L2 language classrooms to design culture-focussed telecollaboration tasks and aid their completion by students.

The paper begins by reviewing traditional approaches and guidance for developing telecollaboration tasks. It then models how tasks can be designed using the popular AI tool “Chat Generative Pre-training Transformer (ChatGPT)” and then simulates how tasks may be completed by learners using ChatGPT-generated information as a springboard for their own culturally appropriate outputs.

The simulated lesson illuminates the potential value of AI tools for teachers and students. However, it also highlights particular aspects of AI literacy that teachers and learners need to be aware of.

This paper has clear practical implications for teacher development by raising awareness of the importance of teachers upskilling in telecollaboration task design and in their understanding of how AI tools can collaborate with them in language classrooms.

The paper adds to the current body of literature on telecollaboration and more specifically adds weight to current discussions taking place around AI tools in language education. By the end of reading the paper, teachers will have a comprehensive grounding in how to use ChatGPT in their classrooms. In doing so, the author demystifies how teachers and students may start exploring these tools in ways that target developing intercultural communicative competence.

This paper provides practical advice for archaeologists and heritage specialists wishing to use ML approaches to identify archaeological features in high-resolution satellite imagery (or other remotely sensed data sources). We seek to balance the disproportionately optimistic literature related to the application of ML to archaeological prospection through a discussion of limitations, challenges and other difficulties. We further seek to raise awareness among researchers of the time, effort, expertise and resources necessary to implement ML successfully, so that they can make an informed choice between ML and manual inspection approaches.

Automated object detection has been the holy grail of archaeological remote sensing for the last two decades. Machine learning (ML) models have proven able to detect uniform features across a consistent background, but more variegated imagery remains a challenge. We set out to detect burial mounds in satellite imagery from a diverse landscape in Central Bulgaria using a pre-trained Convolutional Neural Network (CNN) plus additional but low-touch training to improve performance. Training was accomplished using MOUND/NOT MOUND cutouts, and the model assessed arbitrary tiles of the same size from the image. Results were assessed using field data.

Validation of results against field data showed that self-reported success rates were misleadingly high, and that the model was misidentifying most features. Setting an identification threshold at 60% probability, and noting that we used an approach where the CNN assessed tiles of a fixed size, tile-based false negative rates were 95–96%, false positive rates were 87–95% of tagged tiles, while true positives were only 5–13%. Counterintuitively, the model provided with training data selected for highly visible mounds (rather than all mounds) performed worse. Development of the model, meanwhile, required approximately 135 person-hours of work.

Our attempt to deploy a pre-trained CNN demonstrates the limitations of this approach when it is used to detect varied features of different sizes within a heterogeneous landscape that contains confounding natural and modern features, such as roads, forests and field boundaries. The model has detected incidental features rather than the mounds themselves, making external validation with field data an essential part of CNN workflows. Correcting the model would require refining the training data as well as adopting different approaches to model choice and execution, raising the computational requirements beyond the level of most cultural heritage practitioners.

Improving the pre-trained model’s performance would require considerable time and resources, on top of the time already invested. The degree of manual intervention required – particularly around the subsetting and annotation of training data – is so significant that it raises the question of whether it would be more efficient to identify all of the mounds manually, either through brute-force inspection by experts or by crowdsourcing the analysis to trained – or even untrained – volunteers. Researchers and heritage specialists seeking efficient methods for extracting features from remotely sensed data should weigh the costs and benefits of ML versus manual approaches carefully.

Our literature review indicates that use of artificial intelligence (AI) and ML approaches to archaeological prospection have grown exponentially in the past decade, approaching adoption levels associated with “crossing the chasm” from innovators and early adopters to the majority of researchers. The literature itself, however, is overwhelmingly positive, reflecting some combination of publication bias and a rhetoric of unconditional success. This paper presents the failure of a good-faith attempt to utilise these approaches as a counterbalance and cautionary tale to potential adopters of the technology. Early-majority adopters may find ML difficult to implement effectively in real-life scenarios.

Unlike many high-profile reports from well-funded projects, our paper represents a serious but modestly resourced attempt to apply an ML approach to archaeological remote sensing, using techniques like transfer learning that are promoted as solutions to time and cost problems associated with, e.g. annotating and manipulating training data. While the majority of articles uncritically promote ML, or only discuss how challenges were overcome, our paper investigates how – despite reasonable self-reported scores – the model failed to locate the target features when compared to field data. We also present time, expertise and resourcing requirements, a rarity in ML-for-archaeology publications.