Using Generative AI To Do Research

These are tools where one key feature is generating new text in response to user prompts. They are transformers because they work with enormous amounts of text and employ algorithms to find patterns and relationships in the huge datasets they are trained on (mainly from internet sources). They are commonly referred to as Large Language Models (LLMs) using probability or predictive technology to determine which words should appear in a sequence in response to prompting. 

Different types of text outputs can be generated by these tools in response to prompts, e.g., summaries, reflective statements, blogs, poetry and more.

Examples of text-generating tools include ChatGPT (OpenAI), Google (Gemini), Co-Pilot (Microsoft), Claude (Anthropic), DeepSeek (DeepSeek), and Perplexity (Perplexity AI). Features will vary for different versions and/or for free versus pro models. Consult this guide on Microsoft Copilot from York's University Information Technology Department to learn how best to get access to this tool if you are a York community member, including the Enterprise data protection feature. 

In the Points to Keep in Mind section of Types of Tools, we explain that many of these tools are grounded which means that they incorporate real-time web search and/or an external knowledge base or data source, with the result that they will link to the sources that helped generate their outputs. We recommend checking out tool descriptions to determine when and if this applies, though this feature is common now, even with free versions. It is, however, always recommended that you verify sources and critically evaluating the tool's output. 

These tools generate images from textual descriptions and/or from other images. They work with huge datasets of images and generate outputs based on analysis of those images, including their captions and text descriptions. 

Examples include DALL-E (OpenAI),  ImageFX (Google), Midjourney, Stable Diffusion (Black Technology), Runway (Runway AI), and Adobe Firefly (Adobe).  Note that the big players like ChatGPT (OpenAI), Gemini (Google), and Co-Pilot (Microsoft) now incorporate image-generation features too, with some aspects of this even available in the free versions.

Outputs may take the form of many different types of graphics or media, including cartoons, photos, anime, oil paintings, illustrations and more.

This includes tools like AIVA, Boomy, Soundraw, ElevenLabs, Soundful and Otter.AI. They are designed for audio generation or processing tasks. They are often broken down in to different sub-types including those that facilitate voice generation/cloning, those that facilitate transcription (e.g. meeting notes), and those that generate music or sound effects. Prompts might take the form of text, musical notes, melodies or chord progressions, or audio samples or excerpts. They train on audio data and through this process they can generate new audio that has the style and characteristics of the data they were trained on. 

Outputs may take the form of synthesized voices, sound effects, background soundscapes, and music in the form of songs, melodies, compositions, etc. This can even include new genres of music that mimic existing styles. Outputs may also take the form of written text, i.e. involve speech-to-text applications.

This includes tools like Sora (OpenAI), Runway, Pika, Synthesia, AI Studios (Deepbrain AI), Invideo, and Deforum that generate video content. Prompts can be given in various forms, including text, images, or videos. They are trained on large datasets of video clips, including movies, TV shows, or other video content. Using this data, they are trained to understand and replicate visual patterns and structures in the input video data, as well as temporal and spatial features. Just as with audio tools, these tools can now often assist with video editing and are starting to appear in tools like Adobe Premiere or DaVinci Resolve. 

Outputs can take many forms, including generating simple animations or special effects to complex video scenes or entire movies. 

There are quite a range of tools in this category. They work with scholarly research outputs like articles to search and analyze them, extract key information, generate literature reviews, maps and summaries, or provide features common with citation tools. In a nutshell, they are often billed as helping to automate research workflows. Examples include Elicit, Scite, ResearchRabbit, and Semantic Scholar. 

These tools are much more fully explored in the Research Discovery & Workflow Tools section of this guide. Some of these tools are not 100% free and have usage limits.

These tools help users write code, i.e. they function as code generators or coding assistants. Examples of features include code generation, code behaviour analysis, code review, bug detection, code auto-documentation etc. Some of the best known tools include GitHub Copilot, SourceAI, Tabnine, Qodo, Replit, Amazon Q Developer and Phind.

Note that the big players like ChatGPT (OpenAI), Gemini (Google), and Claude (Anthropic) now incorporate code-generation features too, with some aspects of this even available in the free versions.