用假设答案增强检索，提升问答系统表现。
RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge
- 生成假设答案辅助检索，优化信息获取。
- 通过人工评估获最高综合得分，排名第一。
- 适合关注检索增强生成的算法研究者。
本文介绍RMIT-ADM+S在SIGIR 2025 LiveRAG挑战赛中的获胜系统。我们提出的生成-检索-增强生成（G-RAG）方法，在检索阶段同时使用原始问题和生成的假设答案。G-RAG还引入基于点对点大语言模型的重排序步骤，以优化最终答案生成。我们描述了系统架构及设计思路，特别采用网格点分析法与多因素方差分析（N-way ANOVA），对查询变体生成、问题分解、排序融合策略及答案生成提示技术等配置进行了受控对比。提交系统在人工评估的覆盖率、相关性和质量三项指标上综合得分最高，获得最高Borda分，位列本次挑战赛第一。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。