Retrieval Augmented Generation (RAG): Applications, Limitations, and Future Directions
Abstract
Retrieval Augmented Generation (RAG) is a technique we proposed in 2020 that allows generative AI models to access external information, enhancing their responses to prompts. Since then, the popularity of this approach has skyrocketed, becoming the de facto standard for handling knowledge-intensive tasks in both academia and industry. In this talk, I will describe various applications of RAG, including improving Wikipedia verifiability and providing a glimpse into the work we’re doing at Samaya AI. I will then discuss some limitations of this architecture, such as the “lost in the middle” effect, and conclude by outlining future research directions that I find most exciting.
Fabio Petroni's Biography
Fabio Petroni is the Co-Founder and CTO of Samaya AI, specializing in the intersection of AI and knowledge. He holds a Ph.D. in Engineering of Computer Science from Sapienza University and has extensive research experience at industrial labs, including the FAIR team at Meta AI and the R&D department at Thomson Reuters. Fabio is renowned for his research on knowledge-intensive NLP, highlighted by awards such as first place in the NeurIPS Efficient Open-Domain Question Answering competition in 2020 and the Google Best Paper Award at AKBC 2020. He has authored multiple high-impact publications, including “Language Models as Knowledge Bases?” and the original RAG paper.
Zoom link to attend remotely
https://uniroma1.zoom.us/j/83261382718