Dr. Qinghua Lu1, Dr. Sarvnaz Karimi2, Dr. Stefan Harrer3
1Principal Research Scientist, CSIRO's Data61, Sydney, Australia, 2Principal Research Scientist, CSIRO's Data61, Sydney, Australia, 3Director, AI for Science – Science Digital, CSIRO's Data61 and Adjunct Professor University of Technology Sydney, Melbourne, Australia
Biography:
Dr. Qinghua Lu is a principal research scientist and leads the Responsible AI science team at CSIRO's Data61. She is the winner of the 2023 APAC Women in AI Trailblazer Award. She is part of the OECD.AI’s trustworthy AI metrics project team. She received her PhD from University of New South Wales in 2013. Her current research interests include responsible AI, software engineering for AI/GenAI, and software architecture. She has published 150+ papers in premier international journals and conferences. Her recent paper titled “Towards a Roadmap on Software Engineering for Responsible AI” received the ACM Distinguished Paper Award. Her book, “Responsible AI: Best Practices for Creating Trustworthy AI Systems”, has been published by Pearson Addison-Wesley in Dec 2023.
Dr. Sarvnaz Karimi is a principal research scientist at CSIRO’s Data61, Language Technology Team. She has nearly two decades of experience working in NLP (Natural Language Processing) and Search and Information Retrieval (IR) domains. She applies her expertise at the intersection of IR, NLP, and Machine Learning on different real-world projects in domains such as health, climate adaptation and agriculture. She has led multiple projects in the NLP/IR space over the years. Sarvnaz is active in the research community at large, in Australia and internationally. She is the Director of Publicity at the Association for Computational Linguistics (ACL), the main international professional body for NLP. She was the President of the Australasian Language Technology Association (ALTA), and an executive committee member. She has served as chair, senior area chair, area chair, and Programme Committee member of several major national and prestigious international conferences and journals. Sarvnaz completed a PhD in NLP in 2008 (RMIT University).
Dr. Stefan Harrer is an executive manager-turned scientist in AI and Neuroscience. After 13 years with IBM Research in the US and Australia as IBM Senior Technical Staff Member and Global Lead of Brain-Inspired Computing, and 3 years as Chief Innovation Officer of DHCRC Ltd., Australia’s largest incubator and funder of deep-tech innovation in Digital Health, he joined Australia’s National Science Agency CSIRO in his current role as Director AI for Science. He was featured in WIRED Magazine and Forbes. His framework for the ethical use of AI in the health and life sciences was published by The Lancet in 2023 and has been on its most-read list ever since.
Abstract:
AI is revolutionising science, offering immense potential to tackle complex scientific challenges. CSIRO has recently initiated a strategic research project called Science Digital. The aim of this project is to develop an LLM (Large Language Models) agent platform to assist domain scientists who have limited expertise in AI and software engineering in creating and orchestrating responsible, personalised, proactive, and context-aware agents to help them achieve their research goals more effectively and efficiently. In this talk, we will first provide an overview of the agent platform architecture, highlighting how various design patterns and tools are leveraged to build this platform.
Then, we dive into some of the agents that are specifically designed to assist domain experts in their daily jobs to sift through a large amount of ever-growing scientific literature which relies on identifying relevant content, reviewing, and summarising scientific knowledge, as well as distilling fine-grained information from the literature that could assist with scientific discovery. These agents are created based on Natural language processing and information retrieval techniques, as well as use-case specific evaluation frameworks to ensure their suitability.
This session is intended for scientists that are interested in tools for accelerating scientific discovery. We want to inspire Scientists to think about how they could apply AI and to share proposed tools that could elevate their skill level in applying AI.
The session will be divided into two main parts, starting with the speakers introducing the Science Digital Project and then an interactive session where the audience can ask questions.