How to use the Research Assistant
The Research Assistant is Generative Artificial Intelligence (specifically, Large Language Models or LLM) that lets you explore academic content using natural language. The tool uses most of the content found in our library to identify five documents, then uses the description/abstracts of each source to write an overview of sources. Above the overview, you’ll see the sources used to generate it, along with in-line citations that let you clearly see which source was used to support the overview. Use these sources to explore the topic further and fact-check the tool’s response.
Select a source to see more details about the item, including the abstract and how to access it.
The overview of sources cites each source that it uses to create the overview
Keep in mind that AI-generated answers should be verified for correctness, as they may not always be accurate or up to date.
Research Assistant is not a replacement for human expertise but can be used alongside other research tools to enhance your searching. Research Assistant is designed to make it easier to understand topics, their context, and resources published about them. Use the “view related results within Search It” button to find more documents relevant to your question. Click the AI-generated “related research questions” to explore topics similar to your question.
View related results takes you to a Search It results page with more results based on an AI-generated search string.
Related research questions gives you related questions that you can use to click and run a new search, or think about your topic in different ways.
How are responses generated?
Your question is converted into a search query using a Large Language Model (currently GPT-4.1 Mini). The search engine then identifies the most relevant documents in the index. It ranks them according to how well they can answer the question, and the LLM creates an answer from the top 5 sources.
Because LLMs can generate different responses to the same question, there may be more than one possible answer and different sources that are relevant. If you are not satisfied with the response, use the “Try again” button to generate another.
How to formulate a good question
To make the most of the Research Assistant, it's essential to ask clear and detailed questions about academic or scientific topics. Be as specific as possible and phrase your query in the form of a question. Example queries can be found on the starting screen.
Supported questions/instructions
Research Assistant supports searches in both English and local language searches, answering questions in the language of the query. Most available research material is in English. Note that there is a dependency on the Large Language Model and language support may vary.
You can filter search results by using the filter function on the left-hand side of the search boxes (“What is your research question” box, “Ask your next research question”). Available filters include Articles, Books, peer-reviewed, and date range. You can also ask in your query for specific “recent” materials or ask for sources to only consist of peer-reviewed titles (e.g. “what peer-reviewed articles talk about the influence of plastic waste on marine life”), and the Research Assistant will pick up those words directly from your query. The filter is sticky and will be applied to subsequent searches unless you delete it using the filter dropdown menu or the recycling bin on the right side of the screen.
Filters allow you to select item type, date ranges, and whether the sources are available online.
Unsupported questions/instructions
Research Assistant does not yet support follow-up questions. Each question stands by itself. For example, if you ask “What topics did Simone de Beauvoir write about?”, you cannot follow up by asking “and what is the philosophy of her work” and expect the system to understand what you mean. At this time, you will have to include all relevant information in each question, e.g. “What is the philosophy of Simone de Beauvoir’s work”?
Source types that are included/not included
Research Assistant includes:
- Electronic Articles
- Does not currently include articles from JSTOR, Elsevier, Condé Nast, or DataCite
- E-books
Research Assistant does not include:
- Local print materials
- Newspaper articles
- Media materials (e.g., DVDs and CDs)
- Special collections and archival materials
For a more in-depth look into Research Assistant, visit the ExLibris guide.