AI & ML

By integrating and standardizing diverse datasets, such as publications and other public data sources, along with your internal or third-party data, your AI tools can perform more accurate analyses.  DISQOVER provides powerful querying APIs as well as the ability to provide bulk graph data to feed enterprise data platforms.

By adhering to FAIR data principles, DISQOVER ensures data is findable, accessible, interoperable, and reusable, improving data quality and utility. The platform's best practices, such as defining relationship types, merging concepts, and simplifying data links, optimize ML models. DISQOVER's data visualization capabilities help identify and correct data issues, ensuring reliable and accurate AI/ML outcomes. 

As LLMs are programmed to generate text, not store knowledge, they are prone to accidentally ‘making things up’. That’s where retrieval augmented generation  (RAG) comes to the rescue. By checking the model’s answers against data from the knowledge graph, the LLM can produce a response augmented with knowledge. That improves the accuracy of generative AI models by mitigating the risk of wrongful information production and providing explainability to the generated outcomes.

DISQOVER offers a comprehensive environment for retrieving, normalizing, structuring, and validating knowledge generated through AI or ML. Reintegrating data that was obtained through AI or ML, into DISQOVER, helps users to manage better the information they wish to incorporate into their AI or ML analyses. For instance, include only high-confidence data or exclusively human-generated knowledge.