AI Research Assistant

Q: Will my personal data and information be protected?
A: As of August 6, 2025, Clarivate, the developer of the AI "Research Assistant," assures users a data privacy policy stating that personal data and search history are neither stored for training its large language model nor shared with third parties. Their data policy may change in the future. Please check out their data privacy policy directly at Clarivate.com. 
 

Q: How exactly does Research Assistant work? 

When a user submits a query, the following steps are taken by RA:

• Query Conversion – The user's question is sent to the LLM, where it is converted to a Boolean query that contains a number of variations of the query, connected with an OR. If the query is non-English, some of the variations will be in the query language, and the other variations will be in English.
• Results Retrieval – The Boolean query is sent to the resource index to retrieve the results.
• Re-ranking – The top results (up to 30) are re-ranked using embeddings to identify five sources that best address the user's query.
• Overview Creation – The top five results are sent to the LLM with instructions to create the overview with inline references, based on the abstracts.
• Response Delivery – The overview and sources are returned to the user in the response.

Note the bolded sections – the LLM is only utilized to refine Boolean and produce an overview of results

Q: What’s included in the search results via the AI Research Assistant?  
A: FSU Libraries subscribe to or provide access to more than 900 databases. Searching the Research Assistant does not mean that you are searching all the content available through the library collection. The following sources will NOT be included in the search results. 

• News content (Newspaper articles, Newsletters, Text resources)
• Collections that are not marked as “free for search” in the company's CDI (Central Discovery Index) collection list​
• Sources with insufficient metadata and abstracts that are needed to run the tool effectively.​
• Documents marked as withdrawn or retracted; retraction notes​
• Any collections from the following content providers: APA, DataCite, Elsevier, JSTOR, and Conde Nast
• Any content published by the providers above coming via aggregator collections
• Local records (to be added 2026)
   

Q: How does it differ from traditional chat-based LLMs (ChatGPT, Gemini, Grok, etc.)? 

Unlike chat based Large Language Models (LLMs), Research Assistant is not conversational and does not provide a “back and forth” refinement of queries. RA also does not have the ability to generate creative output – its summary is simply an overview guided by the citations found in our resources. Its main purpose is to refine Boolean queries to help the user find better resources for their search. Additionally, the ONLY results shown are from the index of resources available, so hallucinations or false results are not an issue

Q: Is it necessary to disclose the use of the AI Research Assistant for searching articles or books to an instructor or collaborator?
A: We recommend consulting your course's AI use policy, if available, and seeking guidance from your instructor. Historically, learners and researchers were not required to disclose the use of library catalogs, databases, or internet search engines for literature searches, unless conducting systematic or scoping reviews. The libraries' OneSearch AI Research Assistant operates within a closed environment, unlike general-purpose AI tools such as ChatGPT. Nevertheless, it is always best to confirm with your instructor, as individual policies regarding AI in the classroom can vary.

Q: Can Research Assistant write papers for students? 

No, RA does not have this capability.

Q: What is the window for feedback about this tool? 

We will be accepting feedback until the end of Spring semester 2026. 

Q: How is FSU Libraries seeking feedback? 

Feedback is being collected from our Ask Us chat service, our Research Assistant LibGuide (https://guides.lib.fsu.edu/c.php?g=1480558&p=11054767) and through our library liaisons who are teaching this service.