Scopus AI: Trusted content. Powered by responsible AI.

Scopus AI is an intuitive and intelligent search tool powered by generative AI (GenAI) that delivers insights with unprecedented speed and clarity. Built in close collaboration with the academic community, it provides a window into humanity's accumulated knowledge by surfacing insights from the metadata and abstracts in Scopus, Elsevier’s source-neutral and curated abstract and citation database.

Scopus AI uses natural language processing. That means you don’t have to worry about matching specific keywords or Boolean operators; instead you can just type in your question, statement or hypothetical using everyday language. Scopus AI then locates relevant documents published since 2013 and synthesizes the content of their abstracts to create an instant, easy-to-follow and (importantly) referenced Summary of the information you are seeking. For deeper insights, unique options such as the Expanded summary, Concept map, Foundational papers menu and Topic experts button enable you to continue exploring and learning.

When Scopus AI generates a response to your query, it draws on the metadata and abstracts of the following content types — with the exception of Conference Review, Erratum and Retracted items — published since 2013:

• ●

  Article

• ●

  Book

• ●

  Book chapter

• ●

  Review

• ●

  Short survey

• ●

  Data paper

We chose 2013 as the start year to ensure that the response you receive is based on recent content. For the list of Foundational papers provided by the tool, Scopus AI mines the entire Scopus corpus to provide you with a comprehensive list of influential articles on your chosen topic.

A note about generative AI

While Scopus AI strives to ground its summaries and generative AI features in trusted Scopus content, there may be occasional discrepancies. It is possible for Scopus AI to generate results that could be seen as incorrect, misleading, biased, or even offensive. Scopus AI is not meant to provide legal, financial, or medical advice. Users should not solely rely on Scopus AI outputs without conducting independent research. If you want to utilize Scopus AI generated content in your work, please consult your institutional or workplace guidelines. Do not enter personal, confidential, or sensitive information into Scopus AI.

The vector search engine is updated in near real time, ensuring that the response you receive always considers the latest relevant research available in the Scopus database.

The capabilities of the large language models (LLMs) used in GenAI tools have captured the world’s attention. However, they also come with shortcomings, including a lack of transparency and hallucinations, which can undermine trust in the information they deliver. 

• ●

  Scopus AI minimizes hallucinations and bias by using only high-quality, curated Scopus content identified by our sophisticated vector search. 

• ●

  Scopus AI shows its workings with clear references to the documents it uses to generate its response. It also tells you how confident it is that the response matches your query.  

• ●

  Scopus AI has been designed to avoid unnecessary data retention. The Elsevier Privacy Policy explains how all of our products collect, use and share your personal information. 

• ●

  The content that Scopus AI draws on is peer reviewed and has been rigorously vetted and selected for inclusion in Scopus by the independent Content Selection and Advisory Board.  

• ●

  Scopus AI has been developed and tested in close collaboration with the academic community to ensure it meets key needs and concerns. We continue to work with researchers to enhance the tool.  

• ●

  Scopus AI moves beyond providing just a simple summary response to offer unique features that enable you to continue exploring and learning.  

• ●

  Scopus AI draws on a unique and powerful blend of technology, including our in-house developed and patent-pending RAG fusion algorithm that improves the quality of the search and responses. 

Randomized user testing is one of the many ways that we collect user feedback on Scopus AI.Unfortunately, a user cannot request to be included in user testing because the randomization is a fundamental principle that helps ensure statistical validity.

Scopus AI is now available for your institution to purchase. The exact cost depends on several factors, including whether you are an existing Scopus customer.

If your institution is interested in buying Scopus, Scopus AI, or would like to understand the benefits of combining the two products, please contact your Elsevier account team. New to Elsevier? Visit this page to be connected with an Elsevier representative.

If you are an individual user seeking access to Scopus AI, we recommend reaching out to your library to explore the available options.

As we embed GenAI features in Scopus and other products, we do so in line with Elsevier’s Responsible AI Principles and Privacy Principles. (opens in new tab/window)Scopus AI has been developed and tested in close collaboration with the academic community, to ensure it meets key needs and concerns.

For Scopus AI, we are using OpenAI’s large language model (LLM) ChatGPT hosted on Microsoft Azure and have an agreement in place that information passed to this service will not be stored or used for training purposes. Our use of OpenAI’s LLM is private, meaning there is no data exchange or use of our data to train OpenAI’s public model.

Scopus AI minimizes hallucinations by using only high-quality, curated Scopus content identified by our vector search. This grounds Scopus AI when generating responses. Unlike many other natural language processing tools out there, Scopus AI shows its workings with clear references to the journals and documents it uses to generate a response. In addition, Scopus AI adheres to GDPR to guarantee user privacy. We don't store personal user information or chat history on our systems, unless done so in a compliant way that improves the product (like analytics or personalization). We also don’t share it.

You can also rest easy knowing that the journals that Scopus AI draws on are peer-reviewed and have been rigorously vetted and selected for inclusion in Scopus by independent experts on the Scopus Content Selection and Advisory Board.

The prompt engineering that guides our large language models (LLMs) has been designed to be extremely strict, with clear instructions and scope. For example, the response that Scopus AI generates must match the intent of your query. If the AI can’t find relevant academic papers in Scopus, it must inform you. And when Scopus AI does make a claim or assertion, a reference is always required.

Scopus AI was one of the first products to pioneer what is rapidly becoming the gold standard for LLM use – the retrieval augmented generation (RAG) fusion model. It’s an approach that improves the quality of both vector search retrieval and the generation of LLM summaries.

Scopus AI responses are also regularly tested against two rigorous evaluation frameworks. Together, these factors reduce the risk of hallucinations, and we continue to work on developments to further limit those risks.

We take bias very seriously. Scopus AI draws exclusively on the academic content in Scopus, ensuring transparency by directly referencing the abstracts behind any claims that the tool makes. Our vector search engine employs cosine similarity to identify which abstracts are the closest match to your query rather than favoring the papers that are most cited or published in certain high impact journals. But if your query has a strong bias, it may be reflected in the response. Even if your question is neutral, there may be bias in the Scopus documents that the AI identifies for its response.

One of the ways we attempt to mitigate this is by testing Scopus AI against two rigorous evaluation frameworks. One in particular requires Scopus AI to answer questions linked to areas of potential bias so we can identify and minimize inappropriate responses. And we actively test the service to try and produce responses that create or reinforce unfair bias based on both internal and external queries like Quora’s Insincere Questions Classification.

Our prompt engineering instructs the LLM to filter out 'unsafe' answers that perpetuate prejudice, harm, or stereotypes against individuals from various backgrounds. And where there is bias in a document that Scopus AI uses in a response, it will acknowledge this and provide a reference for the source. We have user-friendly feedback mechanisms so that users can report any harmful or biased responses, which are manually reviewed by our team.

Our current policy is that a GenAI tool cannot be listed or cited as an author, as it is unable to accept responsibility and accountability for its work. In the case of Scopus AI, it is a great learning aid to help you get familiar with a new topic and suggest avenues of exploration. 

Our guidance for authors, reviewers and editors permits the use of GenAI tools to improve the readability and language of the research article, but emphasizes that: 

• ●

  The technology should always be applied as a support tool with human oversight and control. 

• ●

  Results should always be carefully reviewed and edited, where necessary.  

• ●

  Authors should declare if and how they have used a GenAI tool in their paper. 

• ●

  Scopus AI is designed to provide an overview or introduction into a subject or topic based on real academic information. It is not designed to be an absolute source of truth but a guide. For this reason, we recommend that users aim to cite papers directly from the citations in the summaries, rather than citing the summaries themselves.  

• ●

  Further, Scopus AI doesn’t currently include versioning, so the summaries are not suitable for citing.  

We will continue to review this position as the technologies mature. Please note the guidance we link to above only refers to the use of AI tools in the writing/editorial process, and not to the use of AI tools to analyze and draw insights from data as part of the research process. 

Not at the moment, but we are already exploring ways we can enable users to enter queries in their language of choice. Longer term, we will continue working with researchers to understand how expanding the tool’s language capabilities might benefit them.