How to Augment Retrieval Augmented Generation - Jason Coleman скачать в хорошем качестве

How to Augment Retrieval Augmented Generation - Jason Coleman

How to Augment Retrieval Augmented Generation Jason Coleman, Academic Services Librarian, Kansas State University (Hale Library) Retrieval Augmented Generation enables a rapidly expanding class of AI-powered research tools (e.g. Perplexity, Elicit, SciSpace) to conduct searches of articles and/or the broad Internet and then use the results of those searches to cite authentic sources and develop detailed answers. In this session we examine the processes by which these tools translate user-supplied prompts into search queries and then explore how we can use this knowledge to engineer our prompts to increase the relevance and quality of the retrieved results and, concomitantly, the supplied answer. We conclude with a discussion of how librarians can incorporate these methods into research consultations and how we can let our current and potential patrons know that we can help them make better use of these tools.