Skip to Main Content

AI Literacy in the Age of ChatGPT

Other useful AI tools

These tools are based on language models, like those from OpenAI.

Elicit
Find answers from 200 million research papers. Elicit uses semantic similarity, which finds papers related to your question even if they don't use the same keywords. See Getting Started.

NotebookLM
Google's tool for saving and working with your own notes. You can include links to websites, Google Docs, Google Slides, YouTube, or paste in any text and then get useful summaries, quiz questions, and even a simulated podcast based on your content. Learn more in this video. Also, Google never uses your data to train NotebookLM: "your uploads, queries, or the model's responses remain private to you."

Explainpaper
Upload a PDF, highlight confusing text, and get a simpler explanation. Useful for reading research papers outside your field. You can also get explanations in languages other than English.

Inciteful
Build a network of academic papers and it will analyze the network to help you discover the most relevant literature. Select two papers and it will show how the literature connects them together.

Petal
Reference manager and more. Ask the AI to explain your selection, translate it into another language, or identify key points.

Scite AI assistant
A conversational tool made by Scite that lets you ask questions in simple language and get answers backed by real, up to date references. Think of like ChatGPT with real, up to date references, tailor-made for anyone discovering, understanding, or writing research.

What is Deep Research?

Many generative AI systems now have a feature called “Deep Research” — sometimes called “Deep Search” or “Deep Think.” They are designed to generate long reports or literature reviews instead of short answers.  

  • They search, analyze, and synthesize information from hundreds of online sources.
  • They work for several minutes - you can go away and come back later.
  • Their output is a structured report with citations to sources.
  • They use an iterative approach - refining as they go.
  • They are cross-disciplinary - combining information from various domains.
  • They are powered by LLMs, often by reasoning models.

Deep Research is available in free and paid versions of Gemini, ChatGPT, DeepSeek, Grok, Kimi, and Perplexity.  In Claude it’s only found in the paid version. These systems search only open websites, not scholarly content that lives behind paywalls. 

Deep Research functionality is also available in systems that search scholarly data.

For example, Elicit offers a “research report” feature. Elicit searches scholarly data from Semantic Scholar instead of only the web. Undermind, SciScpace, and Ai2 Scholar QA offer a similar feature, also using data from Semantic Scholar.

These are not comprehensive search tools
Since many of these academic systems are based on Semantic Scholar, it’s important to know that the scope of Semantic Scholar is vast, but still smaller than Google Scholar and specialized library databases. So you won’t get a comprehensive search with one of these tools alone.

But they may help you surface research you didn’t find using traditional keyword searching of library databases, because they use semantic search.

Learn more