Skip to Main Content

Generative AI Research Guide

Generative AI Introduction

Generative AI tools are systems that create new content, such as text, images, or code, by learning patterns from large datasets. A common type is the large language model (LLM), which is trained on vast amounts of text to predict and generate language one word at a time based on context. LLMs use neural network architectures to identify statistical relationships in language and produce coherent, human-like responses.

Historical Background

The integration of digital technologies into academic research has also historically come with much controversy. When the internet first emerged as a scholarly tool, some critics were concerned about academic rigor, plagiarism, and non-peer-reviewed sources. However, the internet has enabled unprecedented access to information through online databases, open-access journals, and digital libraries.

Research software has broadened the range of methodological approaches available to scholars across disciplines. Reference management tools have streamlined citation practices, reducing manual effort and improving consistency. Collaborative platforms facilitate distributed research by enabling real-time co-authoring, data sharing, and version control, making them integral to contemporary academic workflows.

AI began as a field in the 1950s with early programs like checkers-playing software by Arthur Samuel and chess algorithms that demonstrated machine learning and strategic reasoning. Over time, AI evolved from rule-based systems to more dynamic applications, including voice assistants like Apple’s Siri, which brought natural language processing into everyday use. Recent advances in AI, especially in machine learning and generative models, have expanded its role in areas like writing, coding, and research support. While widely adopted, AI also raises important questions about authorship, accuracy, and ethical use in academic and public contexts.

What Can These Tools Do?

Generative AI tools can support a wide range of research activities by automating, enhancing, or accelerating various stages of the scholarly process. Here are a few examples:

  • Find sources with prompt engineering

  • Summarize and synthesize academic literature

  • Generate abstracts, outlines, and drafts of research papers

  • Edit and refine scholarly writing for clarity and style

  • Extract key findings from PDFs, datasets, or transcripts

  • Write, debug, and explain code for data analysis or simulations

  • Visualize and interpret data through charts, graphs, or text

  • Brainstorm research questions, hypotheses, or methodologies

  • Translate or rephrase technical content for different audiences or different languages