DeepDyve's AI-Powered Research Assistant

DeepDyve now has a powerful AI feature to help you understand and work with articles: Research Assistant. This article will help you understand how it works and how to use it.

Accessing Research Assistant

To launch Research Assistant, open up an article for reading. Click on "Research Assistant" in the white document bar:

Screenshot of a DeepDyve article page in document mode (tabs: Article, References BETA, Details, Recommended). In the white document bar, an orange arrow points to the highlighted 'Research Assistant' item with an AI icon, next to Bookmark, Print, Add to Folder, Cite, and Social. Below, the enhanced reader shows page 1 of 9 of an article titled 'Identification of Dental Stem Cells Similar to Skeletal Stem Cells'.

In full text mode, click on the AI icon in the top black tool bar:

Screenshot of the enhanced reader in full text mode: an orange arrow points to the highlighted AI icon in the top black tool bar, next to the page controls (Page 1 of 9), settings gear, hand tool, and full-screen icons.

Using Research Assistant

Ask questions about the article you are looking at by typing them in the chat window. For best results, keep your questions short and targeted. Some examples you could try:

Summarize key points of the article

  • Describe the key results from this article and their significance.
  • What is the organism studied in this paper?
  • Summarize the adverse events mentioned in this article
  • What is the date range of data collected?

Create lists or tables of data in the article

  • Please list the software mentioned in this article.
  • Create a table of DNA primers found in this paper. Column 1 is the label. Column 2 is the nucleotide sequence with 5' and 3' specified.

After an answer is provided, you can continue to ask for refinements and further exploration. To begin a new conversation, click "Reset Conversation"

Screenshot of the Research Assistant chat area: an empty question text box with a blue 'Send' button, and an orange arrow pointing to the highlighted 'Reset Conversation' button used to begin a new conversation.

Using Research Assistant on multiple documents

In addition to querying the article you're looking at, you can choose to add up to four items from that article's references. To use this feature, click on "Include References":

Screenshot of the Research Assistant chat area with a banner reading 'Chat with this article.' An orange arrow points to the highlighted 'Include References' link with a pencil icon — clicked to add up to four of the article's references to the conversation.

Select up to four references and the click "Confirm Selection".

Screenshot of the 'Chat with Multiple Articles' dialog: 'Select up to four references to include in a new chat with Research Assistant'. Three references are listed with green checkboxes (author lists, years, titles, and journals), with 'Cancel' and blue 'Confirm Selection' buttons at the bottom.

To see which articles are included, click the arrow. To select a different set of articles, click "Change References".

Screenshot of the Research Assistant chat area with the banner 'Chat with this article and 4 references.' Orange arrows point to the expander arrow (to see which articles are included) and to the 'Change References' link with a pencil icon (to select a different set of articles).

What articles does Research Assistant work with?

Research Assistant currently works with tens of millions of full-text papers from our OA and LitStream collections, as well as PDFs you upload to your My Papers repository, and for Enterprise customers, PDFs uploaded to the Research Archive.


Please note that not every publisher in our OA and LitStream collections have included all their works, so you may encounter a paper where this feature is unavailable. But rest assured that we are continuing to work with our partners to expand this feature to every paper in DeepDyve.

How confidential are my queries?

DeepDyve has developed its own AI features but also relies on the large language model (LLM) from OpenAI, Anthropic and other potential AI vendors, via their Enterprise API license. Under the terms of these licenses, the LLMs will neither store any data passed to them, nor use that data to train their models. Further, DeepDyve is not including any client or user-specific information in the API to ensure even greater confidentiality

Still need help? Contact Us Contact Us