Exploring the potential of large language models and generative artificial intelligence (GPT): Applications in Library and Information Science

Abstract

The presented study offers a systematic overview of the potential application of large language models (LLMs) and generative artificial intelligence tools, notably the GPT model and the ChatGPT interface, within the realm of library and information science (LIS). The paper supplements and extends the outcomes of a comprehensive information survey on the subject matter with the author’s own experiences and examples showcasing possible applications, demonstrated through illustrative instances. This study does not involve testing available LLMs or selecting the most suitable tool; instead, it targets information professionals, specialists, librarians, and scientists, aiming to inspire them in various ways. Within this paper, we explore both well-known and less recognized use cases of generative AI tools, which may prove relevant not only for the target group of information specialists but also for other users. Our analysis demonstrates that apart from merely summarizing or expanding existing textual content, these AI tools hold the potential for performing non-standard yet sophisticated tasks with electronic information resources. They can facilitate interactive engagement with these resources, aid in the extraction and composition of descriptive metadata, indexing, and even possible classification. Nevertheless, it is essential to acknowledge the numerous limitations of current LLMs, which we acknowledge in this study.