Introducing Copilot, a new feature for Scopus AI to handle specific and complex queries
Since the launch of Scopus AI last year, we’ve learned that it delivers great results when exploring a specific research area but can struggle to handle queries that are a bit too specific – for example, those that ask about a certain gene or rare medical condition. Some topics are so niche there may be only a handful of papers that describe them.
To address this need, we’re pleased to introduce the first in a lineup of new features for Scopus AI called Copilot, which is designed to optimize responses to highly specific or complex queries. Copilot uses both keyword and vector search tools, employing more and varied types of search technology to better process specialized queries and provide more specific responses.
Here's how Copilot works:
- Copilot looks at the content of your query and decides whether to run a vector search and/or keyword search
- It then ensures complex queries are broken down into their component parts and are optimized for the search channels it has chosen to use; for example, for the keyword search it adds Boolean operators
- In doing so, it considers more abstracts than the previous search
As a result of this process, Copilot can break down more complex queries into their individual components and optimize each element for either vector or keyword search. This means users can pose more complicated or multifaceted questions, and Copilot will be able to sift through the different aspects to produce the best possible results.
Support of non-English queries
We realize exploring a new topic area can be difficult enough if English is your first language. But if English isn’t your native language, delving into new subjects can be even more challenging. To address this issue, Copilot also includes an intelligent language layer, which can take a query in a non-English language and translate it into English, which is the language many researchers say they prefer to work in.
Copilot improves Scopus AI in other ways, including:
- Automatic correcting of spelling mistakes to provide the clearest responses possible
- Processing of longer text queries, including full abstracts
- Expanding the number of search results Scopus AI provides - up from 10 in the summary and 20 in the expanded summary to a new upper limit of 30
In line with Elsevier’s Responsible AI principles, Copilot provides a unique transparency layer that explains exactly how the tool is breaking down and optimizing your query. This is a unique feature among GenAI solutions currently on the market, and another step towards refining this exciting new tool.
The research community has been closely involved in every step of the Scopus AI development process, and the introduction of Copilot has also been the result of customer feedback. Testing and offline evaluation has shown Copilot greatly improves the quality of the results produced and enables Scopus AI to support a wider range of queries, from highly niche to very broad.
With Copilot, we hope to provide an even more nuanced and specialized view into the evolving world of academic research.