RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911073750220800 |
|---|---|
| author | Ran, Kun Sun, Shuoqi Anh, Khoi Nguyen Dinh Spina, Damiano Zendel, Oleg |
| author_facet | Ran, Kun Sun, Shuoqi Anh, Khoi Nguyen Dinh Spina, Damiano Zendel, Oleg |
| contents | This paper presents the RMIT--ADM+S winning system in the SIGIR 2025 LiveRAG Challenge. Our Generation-Retrieval-Augmented Generation (G-RAG) approach generates a hypothetical answer that is used during the retrieval phase, alongside the original question. G-RAG 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 approach and N-way ANOVA enabled a controlled comparison of multiple configurations, including query variant generation, question decomposition, rank fusion strategies, and prompting techniques for answer generation. The submitted system achieved the highest Borda score based on the aggregation of Coverage, Relatedness, and Quality scores from manual evaluations, ranking first in the SIGIR 2025 LiveRAG Challenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_14516 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge Ran, Kun Sun, Shuoqi Anh, Khoi Nguyen Dinh Spina, Damiano Zendel, Oleg Information Retrieval This paper presents the RMIT--ADM+S winning system in the SIGIR 2025 LiveRAG Challenge. Our Generation-Retrieval-Augmented Generation (G-RAG) approach generates a hypothetical answer that is used during the retrieval phase, alongside the original question. G-RAG 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 approach and N-way ANOVA enabled a controlled comparison of multiple configurations, including query variant generation, question decomposition, rank fusion strategies, and prompting techniques for answer generation. The submitted system achieved the highest Borda score based on the aggregation of Coverage, Relatedness, and Quality scores from manual evaluations, ranking first in the SIGIR 2025 LiveRAG Challenge. |
| title | RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2506.14516 |