Academic search and discovery tools in the age of AI and large language models: An overview of the space

• Main Author: TAY, Aaron
• Format: text
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Artificial Intelligence and Robotics; Data Science; Library and Information Science
• Online Access: https://ink.library.smu.edu.sg/ai_research_week/Programme/Programme/1; https://ink.library.smu.edu.sg/context/ai_research_week/article/1002/viewcontent/Academic_Search___Discovery_Tools_in_the_Age_of_AI___Large_Language_Models___An_Overview_of_the_Space_.pdf
• Institution: Singapore Management University

In the ever-evolving landscape of academic research, “AI tools” for literature search and synthesis are currently getting a lot of attention. These tools promise to ramp up productivity, enabling us to accomplish more in less time or absorb more knowledge without drowning in endless reading. With the sheer number of these systems increasing daily, it's natural to wonder: are they really worth our time and money? And if they are, how should we go about picking the right one from the multitude of options? In this talk, I will share my views on how the space has developed over two increasingly popular but distinct set of what many call “AI tools”. The first is what I have dubbed “Citation based literature mapping tools”, which includes tools like Connected Papers, ResearchRabbit and Litmaps. Secondly, the rise of transformer based large language (LLMs) models like OpenAI’s GPT models has also great implications on how academic discovery might change and in this talk I will highlight the 3 main ways in which the Natural language understanding and natural language understanding capabilities of LLMs are being used in currenct academic search engines such as Elicit, SciSpace and Scite assistant and the limits of such tools.