Bildschirmfoto 2023-10-05 um 09.50.25

ris.ai Unveils Researcher Workspace 1.0, an Accuracy-First AI Assistant for Scientific Researchers

Norway – 5th October – Iris.ai, provider of a world-leading and award-winning AI engine for scientific text understanding, has released the Researcher Workspace 1.0, a new platform that uses Natural Language Processing (NLP) to accelerate scientific research, putting factual accuracy first. Researchers can access a comprehensive AI tool suite powered by Iris.ai’s unique technology, including a brand new Chat feature, to search, explore, and extract information from swathes of scientific documents all in one place without compromising privacy.

The Researcher Workspace’s uniquely comprehensive tool suite includes the Chat feature, content-based search, context and data filtering, data extraction from text and tables, document set analysis, and summarisation.

Given the pressing need for accuracy in scientific research, as well as the well-publicised hallucinations of many Large Language Models (LLMs), Iris.ai has developed a method to measure the factual accuracy of AI-generated content – testing precision and recall, fact tracing, and extraction. Using knowledge graphs and a universal metric named WISDM, designed by the company, Iris.ai tests context similarity to confirm factual accuracy.

Factuality is a central design principle of the Workspace, and Iris.ai’s researchers have leveraged knowledge graphs to significantly reduce errors and deliver accurate results. Preliminary tests of the Chat functionality show that features soon to be introduced have reduced hallucinations down to single-figure percentages.  To maximise privacy, Iris.ai’s models only interact with user content for the specific session or operation requested, never learning or storing document information. In addition, all necessary model training uses external domain knowledge, ensuring that customers’ company secrets are always safeguarded.

Iris.ai has used its proprietary AI techniques, expertise, and algorithms to deliver better results for customers at lower costs – enhancing the scientific and patent research of multinational corporations such as steelmaker ArcelorMittal, public bodies like the Finnish Food Authority, and research institutions, including the University of Helsinki. In January 2023, it was awarded up to €14.4 million by the European Innovation Council to support European scientific research and AI development against a growing competitive landscape, including the US and China.

Anita Schjøll Abildgaard, CEO and Co-founder of Iris.ai, commented, “The Researcher Workspace 1.0 is the product of seven years of research and development, based on the latest in AI, machine learning, and NLP technology. This is a game-changer for scientific researchers, and we’re grateful to our clients and customers who’ve been invaluable in our journey along the way.

Abildgaard continued, “The Researcher Workspace 1.0’s ability to help researchers navigate, evaluate, and draw insights from thousands of research documents  in hours, not months, can accelerate the pace of discovery and innovation and help us tackle some of the biggest problems of our age: our clients are working on topics like climate change, plastic pollution, human health, and the spread of disease.

“We are determined to build on our selection for the European Innovation Council Accelerator funding, using our proprietary techniques, developed through years of research and development, to deliver better results for our clients at more affordable costs. With this release, we are one step closer to our goal of building a complete AI researcher – AI tools and applications which allow humans to make sense of the totality of the world’s scientific knowledge.”

The Researcher Workspace is available for users with Iris.ai business licences and will be available for individual subscribers later this autumn. Sign up here to join the waitlist.