Library Search AI Research Assistant

The Research Assistant is a tool powered by Generative Artificial Intelligence (specifically, Large Language Models or LLM). It allows you explore academic content by asking questions in natural language. The tool uses most of the content found in your library to identify five documents that can help answer your question. It then extracts the most relevant information from the description/abstracts of each source to write the answer. Above the answer, you’ll see the sources used to generate it along with in-line citations that let you clearly see which source was used to generate each part in the answer. Use these sources to delve deeper into the topic and to fact check the responses from the tool. Keep in mind that AI-generated answers should be verified for correctness, as they may not always be accurate or up-to-date.

The Research Assistant is not a replacement for human expertise but uses artificial intelligence to automate otherwise time-consuming tasks. Clarivate has designed the Research Assistant make it easier to understand topics, their context, and resources published about it. Use the “view related results on your library search” button to find more documents relevant to your question. Click the AI-generated “related research questions” to explore topics similar to your question.

How are responses generated?

Your question is converted into a query that the search engine understands with the help of a Large Language Model (currently GPT 4o-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, again with the help of the Large Language Model, creates an answer from the top 5 sources.

Due to the nature of Large Language Models, answers to the same question are not always the same. There may be more than one possible answer and different resources that are relevant. If you are not satisfied with your answers, use the “Try again” button.

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

The Research Assistant supports local language searches. Most material in our index is in English. If you ask a question in another language than English, the Assistant will search in both, your local language and English, and write the answer in the language of your question. Note that there is a dependency on the Large Language Model and language support may vary.

The Research Assistant allows you to specify resource types, and dates, for example if you are looking specifically for books or articles about a topic, or works from a certain date range. The Research Assistant will use this information to filter the results accordingly. For example, you can ask for sources to only consist of peer reviewed titles (e.g. “what peer review articles talk about the influence of plastic waste on marine life”). Available filters are Articles, Books, peer reviewed and a date range. In addition, if you ask in your query for example for “recent” or “the latest” material, the Research Assistant will filter the results by what was published in the last 5 years. While the Research Assistant will pick up those words directly from your query, you can also use the filter function on the lefthand side of the search boxes ( “What is your research question” box, “Ask your next research question”). The filter is sticky and will be applied to subsequent queries unless you delete it, either by changing the value in the filter dropdown, or by using the recycling bin on the right side of the screen.

Tip: If you want to rerun the same search as before - for example after you chose a filter - you can click into the “Ask your next research question” box and hit the “arrow up” key on your keyboard.

Unsupported questions/instructions

The 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”?