融合有标签与无标签数据，提升检索增强生成效果
HF-RAG: Hierarchical Fusion-based RAG with Multiple Sources and Rankers
- 用分源聚合+z-score标准化融合多模型检索结果
- 在事实验证任务中超越单一模型，跨域泛化更强
- 适合需要高可靠性生成的问答与验证场景
结合有标签数据（输入-输出关联）和无标签数据（更广上下文）可在检索增强生成（RAG）中带来互补优势。然而，由于不同来源的相似度分数不可直接比较，有效融合异构信息颇具挑战。此外，整合多个排序器的输出可提升RAG性能。本文提出的方法首先对每个来源（有标签与无标签）使用标准排序融合技术聚合多个信息检索模型的前K篇文档；随后在每类来源内通过z-score变换标准化检索得分分布，再合并两类来源的最优检索结果。我们在事实验证任务上评估该方法，结果表明其持续优于表现最佳的单一排序器或数据源，并展现出更强的跨域泛化能力。
原文摘要 · Abstract (English)
Leveraging both labeled (input-output associations) and unlabeled data (wider contextual grounding) may provide complementary benefits in retrieval augmented generation (RAG). However, effectively combining evidence from these heterogeneous sources is challenging as the respective similarity scores are not inter-comparable. Additionally, aggregating beliefs from the outputs of multiple rankers can improve the effectiveness of RAG. Our proposed method first aggregates the top-documents from a number of IR models using a standard rank fusion technique for each source (labeled and unlabeled). Next, we standardize the retrieval score distributions within each source by applying z-score transformation before merging the top-retrieved documents from the two sources. We evaluate our approach on the fact verification task, demonstrating that it consistently improves over the best-performing individual ranker or source and also shows better out-of-domain generalization.
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。