Natural Language Search (NLS) is an AI-powered feature that allows users to enter queries in plain, everyday language.
NLS uses Natural Language Understanding (NLU), a form of artificial intelligence that focuses on interpreting user input rather than generating new content. This system uses large language models that have been designed to better understand and process your academic search questions. It does not use generative AI and is not trained on user data. It breaks your search into important terms and topics, then runs it through EBSCO's search system to find the most relevant and useful results instead of just matching words.
Key benefits include:
⚠️ Accuracy may vary depending on how clearly the query is written. [See prompt engineering]
⚠️ Some results may still require refinement using advanced filters and traditional search techniques.
⚠️ Not all records will show significant improvements, especially those with limited metadata.
The Oxford Academic AI Discovery Research Assistant is a helpful tool for finding articles, book chapters, and other research content. The tool uses a version of ChatGPT called GPT-4o mini enhanced through a retrieval-augmented generation (RAG) system to provide a list of 10 "relevant" resources based on the prompt. While it is a great way to start your research, it does not save your past searches, cannot read uploaded documents, and it not immune to occasional inaccuracies or "hallucinations." However, it makes finding academic information faster and easier, especially when you are not sure what specific terms to use.
JSTOR's AI research tool helps users explore and understand scholarly content. After creating a personal account, the tool will appear alongside articles, book chapters, and research reports. It offers AI-driven prompts and explanations to help you analyze the entire text or specific passages.
You can:
This tool is continually being updated, and usage guidance including how JSTOR approaches generative AI is available in their FAQs.
Includes all 2,800+ academic journals on JSTOR that span more than 60 disciplines across the humanities, social sciences, and natural sciences, along with millions of primary sources across four collections.
