ADM+S researchers Oleg Zendal and Damiano Spina being presented with their team’s award at the 2025 ACM SIGIR international conference.Abstract
This talk presents the RMIT-ADM+S participation in the SIGIR 2025 LiveRAG Challenge. Our Generation-Retrieval-Augmented Generation (GRAG) approach relies on generating a hypothetical answer that is used in the retrieval phase, alongside the original question. GRAG also incorporates a pointwise large language model (LLM)-based re-ranking step prior to final answer generation. We describe the system architecture and the rationale behind our design choices. In particular, a systematic evaluation using the Grid of Points (GoP) framework and N-way ANOVA enabled comparison across multiple configurations, including query variant generation, question decomposition, rank fusion strategies, and prompting techniques for answer generation. Our system achieved a Relevance score of 1.199 and a Faithfulness score of 0.477 on the private leaderboard, placing the first place in the LiveRAG 2025 Challenge.
🏆 ADM+S team wins global LiveRAG Challenge at SIGIR 2025
Source: ADM+S Centre News.
Getting There
Kun Ran
Developer at RMIT ADM+S Centre
Kun is a developer at RMIT ADM+S Centre, he just got his Master of AI from RMIT University. His minor thesis focuses on measuring effectiveness for query variants in information retrieval. His current research goal including Retrieval Augmented Generation (RAG) and the comparative effectiveness against traditional search experience.
Chenglong Ma
Research Fellow
I’m a Research Fellow at ADM+S RMIT node. My research interests include Information Retrieval, Recommender Systems, and Responsible AI.