Report on the 1st Workshop on Information Retrieval's Role in RAG Systems (IR-RAG 2024) at SIGIR 2024
Fabio Petroni, Federico Siciliano, Fabrizio Silvestri, Giovanni Trappolini · ACM SIGIR Forum · 2024
Retrieval-Augmented Generation (RAG) systems have become a transformative component of artificial intelligence, combining the strengths of information retrieval (IR) and generative models to tackle complex problems in diverse domains. Despite their rapid adoption and proven potential, the role of IR within RAG frameworks remains under-explored, with research often prioritising advances in generative techniques. This imbalance has left a critical gap in understanding how robust retrieval mechanisms can optimise the overall performance and reliability of RAG systems. The 1st Workshop on Information Retrieval's Role in RAG Systems (IR-RAG), held at SIGIR 2024, addressed this gap by focusing on the fundamental principles of information retrieval within the RAG paradigm. The workshop provided a dedicated platform for researchers, practitioners, and experts to share insights, foster discussions, and present innovative research highlighting the centrality of IR in RAG frameworks. Through keynote talks, oral and poster presentations, and collaborative breakout sessions, the workshop highlighted both the challenges and opportunities in refining retrieval methodologies to support the generative components of RAG systems. This event has set the stage for advancing research on IR's pivotal role in shaping the future of RAG systems. The proceedings of the workshop, published in CEUR Workshop Proceedings, are available at https://ceur-ws.org/Vol-3784/. Date : 18 July 2024. Website : https://coda.io/@rstless-group/ir-rag-sigir24.