A generative-AI-powered tool that helps you quickly find the right content and easily navigate complex research tasks.
Learn more
The Web of Science Research Assistant helps researchers at all levels get more out of the world’s most trusted citation database—Web of Science Core Collection. Swiftly explore over a century of research. Easily gather high-value insights that will advance your research project. Approach your topic from a new vantage point—all while using a tool aligned with responsible AI principles.
Confidently source relevant, trusted content and data that directly supports your research goals. Improve your research process with insightful views of the research landscape and free up valuable time for activities that add new knowledge to the ecosystem.
Implement responsible AI tools
Flexible search for documents
Conduct natural language searches in several languages and receive overviews that consider over 120 years of research and reveal connections between concepts and papers in a field of study.
Guided prompts and workflows
Approach Web of Science with a research task in mind and receive suggestions for ways to enhance your research workflow. Follow context-specific prompts to expand or narrow the scope of your discovery.
Unique data visualizations
Explore graphs and tables oriented toward a research task, such as a literature review, that show different angles on a topic and guide you deeper. Browse useful maps of the research landscape without having to build them yourself.
When you submit a question to the assistant, it starts by retrieving articles that exhibit the highest degree of semantic similarity to your query and then complements those with additional highly relevant results based on keywords. From there, it ranks results based on a similarity score and runs them through a proprietary algorithm to ensure that the most valuable and pertinent resources are highlighted. Top publications are then chosen to formulate a response to your query. Additional layers of relevancy ranking reduce noise in your results sets.
The Web of Science Research Assistant is currently in beta testing with our development partners.
We use commercially provided pre-trained Large Language Models in a Retrieval Augmented Generation architecture (RAG). We do not train our own models. While we are using the pre-trained LLMs to support the creation of narrative content, the facts in this content are generated from our trusted academic sources. We test this setup rigorously to ensure academic integrity and alignment with the academic ecosystem. Testing includes validation of responses through academic subject matter experts who evaluate the outputs for accuracy and relevance. Additionally, we conduct extensive user testing that involve real-world research and learning scenarios to further refine accuracy and performance.
We are committed to the highest standards of user privacy and security. We do not share or pass any publisher content, library-owned materials, or user data to large language models (LLMs) for any purpose.
We are not using any of the LLM API endpoints directly but accessing it from a private space. This ensures that data entered by users in the query will not be accessible to any other party.
We have developed the Clarivate Academic AI Platform that is designed to help us bring existing and new solutions to the market faster and support multiple use cases at scale. The platform will allow us to deliver more capabilities, such as semantic search and more, with a consistent user experience, in a safe and secure environment that ensures user privacy and data security. The platform will serve all Clarivate academic solutions.
The AI Platform is not just about infrastructure. The AI Platform team serves as an AI center of excellence with strong LLM stewardship, supporting the different product teams in using AI responsibly, and providing strong governance to make sure that AI is applied responsibly. The team also works closely with the community. They have built an AI Advisory council, with the goal of sharing insights & findings, evaluating results, gathering feedback from librarians, students, and faculty, mitigating inaccuracies & bias issues, and sharing adoption best practices.
