RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge

This paper 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 among the top four finalists in the LiveRAG 2025 Challenge.

@article{ran2025_2506.14516,
  title={ RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge },
  author={ Kun Ran and Shuoqi Sun and Khoi Nguyen Dinh Anh and Damiano Spina and Oleg Zendel },
  journal={arXiv preprint arXiv:2506.14516},
  year={ 2025 }
}