Search results

In terms of training the public in prompt engineering skills, no single discipline or profession currently takes the lead, presenting an opportunity for professions like librarianship to step into this role. Librarians are already well-equipped to educate the public in a wide range of literacy skills and tasks, so prompt engineering may be a natural progression. The purpose of this paper is to examine the potential role of prompt engineering for library professionals.

Prompt engineering is the process of optimizing the text that is provided to an artificial intelligence (A)I model to ensure proper interpretation and the generation of relevant, detailed results. The field of prompt engineering is relatively young, evolving alongside the growth of large language models like ChatGPT and BARD. This conceptual paper will explore prompt engineering as a possible domain of expertise for librarians.

This paper delves into the world of prompt engineering, its alignment with the existing roles and expertise of librarians, and the potential emergence of a new role known as the “prompt engineering librarian,” akin to the well-established “information literacy librarian” role that has gained prominence in recent decades.

The significance of this work lies in exploring the synergy between prompt engineering and the traditional roles of librarians, highlighting the potential for a new and valuable profession in the form of prompt engineering librarians. This innovative concept could bridge the gap in AI literacy and facilitate more effective interactions with AI systems, contributing to the broader goal of AI accessibility and understanding.

The researchers conducted a collective case study to investigate how families engaged in making activities related to aerospace engineering in six pop-up makerspace programs held in libraries and one museum. The purpose of this paper is to support families’ engagement in design tasks and engineering thinking, three types of discussion prompts were used during each workshop. The orienting design conjecture was that discussion prompts would allow parents to lead productive conversations to support engineering-making activities.

Within a collective case study approach, 20 consented families (22 adults, 25 children) engaged in making practices related to making a lunar rover with a scientific instrument panel. Data included cases of families’ talk and actions, as documented through video (22 h) and photographs of their engineering designs. An interpretivist, qualitative video-based analysis was conducted by creating individual narrative accounts of each family (including transcript excerpts and images).

Parents used the question prompts in ways that were integral to supporting youths’ participation in the engineering activities. Children often did not answer the astronomer’s questions directly; instead, the parents revoiced the prompts before the children’s engagement. Family prompts supported reflecting upon prior experiences, defining the design problem and maintaining the activity flow.

Designing discussion prompts, within a broader project-based learning pedagogy, supports family engagement in engineering design practices in out-of-school pop-up makerspace settings. The work suggests that parents play a crucial role in engineering workshops for youths aged 5 to 10 years old by revoicing prompts to keep families’ design work and sensemaking talk (connecting prior and new ideas) flowing throughout a makerspace workshop.

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.

Following the recent rise in generative artificial intelligence (GenAI) tools, fundamental questions about their wider impacts have started to reverberate around various disciplines. This study aims to track the unfolding landscape of general issues surrounding GenAI tools and to elucidate the specific opportunities and limitations of these tools as part of the technology-assisted enhancement of mechanical engineering education and professional practices.

As part of the investigation, the authors conduct and present a brief scientometric analysis of recently published studies to unravel the emerging trend on the subject matter. Furthermore, experimentation was done with selected GenAI tools (Bard, ChatGPT, DALL.E and 3DGPT) for mechanical engineering-related tasks.

The study identified several pedagogical and professional opportunities and guidelines for deploying GenAI tools in mechanical engineering. Besides, the study highlights some pitfalls of GenAI tools for analytical reasoning tasks (e.g., subtle errors in computation involving unit conversions) and sketching/image generation tasks (e.g., poor demonstration of symmetry).

To the best of the authors’ knowledge, this study presents the first thorough assessment of the potential of GenAI from the lens of the mechanical engineering field. Combining scientometric analysis, experimentation and pedagogical insights, the study provides a unique focus on the implications of GenAI tools for material selection/discovery in product design, manufacturing troubleshooting, technical documentation and product positioning, among others.

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.

This paper aims to provide a comprehensive analysis of the transformative impact of Artificial Intelligence (AI) and Large Language Models (LLMs), such as GPT-4, on the real estate industry. It explores how these technologies are reshaping various aspects of the sector, from market analysis and valuation to customer interactions and evaluates the balance between technological efficiency and the preservation of human elements in business.

The study is based on an analysis of the strengths and weaknesses of AI as a technology in applications for real estate. It uses this framework to assess the potential of this technology in different use cases. This is supplemented by an emerging literature on the topic, practical insights and industry expert opinions to provide a balanced perspective on the subject.

The paper reveals that AI and LLMs offer significant benefits in real estate, including enhanced data-driven decision-making, predictive analytics and operational efficiency. However, it also uncovers critical challenges, such as potential biases in AI algorithms and the risk of depersonalising customer interactions.

The paper advocates for a balanced approach to adopting AI, emphasising the importance of understanding its strengths and limitations while ensuring ethical usage in the diverse and complex landscape of real estate.

This work stands out for its balanced examination of both the advantages and limitations of AI in real estate. It introduces the novel concept of the “jagged technological frontier” in real estate, providing a unique framework for understanding the interplay between AI and human expertise in the industry.

This viewpoint article explores the transformative capabilities of large language models (LLMs) like the Chat Generative Pre-training Transformer (ChatGPT) within the property valuation industry. It particularly accentuates the pivotal role of prompt engineering in facilitating valuation reporting and advocates for adopting the “Red Book” compliance Chain-of-thought (COT) prompt engineering as a gold standard for generating AI-facilitated valuation reports.

The article offers a high-level examination of the application of LLMs in real estate research, highlighting the essential role of prompt engineering for future advancements in generative AI. It explores the collaborative dynamic between valuers and AI advancements, emphasising the importance of precise instructions and contextual cues in directing LLMs to generate accurate and reproducible valuation outcomes.

Integrating LLMs into property valuation processes paves the way for efficiency improvements and task automation, such as generating reports and drafting contracts. AI-facilitated reports offer unprecedented transparency and elevate client experiences. The fusion of valuer expertise with prompt engineering ensures the reliability and interpretability of valuation reports.

Delineating the types and versions of LLMs used in AI-generated valuation reports encourage the adoption of transparency best practices within the industry. Valuers, as expert prompt engineers, can harness the potential of AI to enhance efficiency, accuracy and transparency in the valuation process, delivering significant benefits to a broad array of stakeholders.

The article elucidates the substantial impact of prompt engineering in leveraging LLMs within the property industry. It underscores the importance of valuers training their unique GPT models, enabling customisation and reproducibility of valuation outputs. The symbiotic relationship between valuers and LLMs is identified as a key driver shaping the future of property valuations.

In January 2016, Georgia Tech launched a campus-wide academic initiative (“Center for Serve-Learn-Sustain”) aimed at preparing undergraduate students in all majors to use their disciplinary knowledge and skills to contribute to the major societal challenge of creating sustainable communities. The initiative calls for faculty members from all six Georgia Tech colleges to develop courses and co-curricular opportunities that will help students learn about sustainability and community engagement and hone their skills by engaging in real-world projects with nonprofit, community, government, and business partners. Affiliated courses address various aspects of the Center’s sustainable communities framework, which presents sustainability as an integrated system connecting environment, economy, and society. This chapter reports on one engineering instructor’s ongoing efforts that bring sustainability into the engineering classroom through sociotechnical project-based learning. This cornerstone design course is one of more than 100 Center-affiliated courses currently offered; the full set of Center-affiliated courses enrolls over 5,000 students per year across all six colleges. The sustainability activities introduced in the freshman design course pertain particularly to the Center’s vision that all graduates of the institute, a majority of whom will graduate with engineering degrees, are able to contribute to the creation of sustainable communities and to understand the impact of their professional practice on the communities in which they work. A situated knowledge and learning pedagogical theory is used in the Center-affiliated course, where concept, activity, and context are involved in student learning to produce useable robust knowledge. The sociotechnical project-based teaching model with contextualized design problems is used to engage students throughout the course by utilizing computer-aided-design problems that incorporate sustainability within both individual and team projects. In this chapter, the authors present the pedagogical approaches to learning, strategies, and challenges for implementation and assessment of intervention activities, and data analyses of both student reflection data and pre- and post-survey data.

This paper aims to investigate how families’ sociomaterial experiences in engineering programs held in libraries and a museum influence their creative engineering practices and the creativity expressed in their products derived from their inquiry-driven engineering activities.

This research project takes a naturalistic inquiry using qualitative and quantitative analyses based on video records from activities of 31 parent–child pairs and on creativity assessment of products that used littleBits as prototyping tools.

Families engaged in two sociomaterial experiences related to engineering – collaborative idea exchange and ongoing generative tinkering with materials – which supported the emergence of novel ideas and feasible solutions during the informal engineering programs. Families in the high novelty score group experienced multiple instances of collaborative idea exchange and ongoing generative tinkering with materials, co-constructed through parent-child collaboration, that were expansive toward further idea and solution generation. Families in the low novelty score group experienced brief collaborative idea exchange and material tinkering with specific idea suggestions and high involvement from the parent. An in-depth case study of one family further illustrated that equal engagement by the parent and child as they tinkered with the technology supported families’ creative engineering practices.

This analysis adds to the information sciences and learning sciences literatures with an account that integrates methodologies from sociocultural and engineering design research to understand the relationship between families’ engagement in creative engineering practices and their products. Implications for practitioners include suggestions for designing spaces to support families’ collaborative idea exchange and ongoing generative tinkering to facilitate the development of creative engineering practices during short-term engineering programs.