用更丰富的命题路径搜索，提升大模型多跳推理的准确性
PropRAG: Guiding Retrieval with Beam Search over Proposition Paths
- 用上下文完整的命题替代三元组，更好保留知识语境
- 无需依赖大模型，直接用束搜索高效发现多步推理路径
- 在多个数据集上刷新零样本召回率与精确率纪录
检索增强生成（RAG）已成为为大语言模型注入最新知识的标准方法。然而，传统RAG依赖独立段落检索，难以捕捉复杂多跳推理所需的关联信息。尽管结构化RAG通过三元组构建知识图谱尝试解决此问题，但三元组固有的上下文丢失（上下文坍缩）限制了知识表示的保真度。本文提出PropRAG，一种新型RAG框架，将知识表示从三元组转向富含上下文的命题，并引入无需大模型的在线束搜索机制，以高效发现多步推理路径。通过更高保真度的知识表征与显式路径探索，PropRAG在2Wiki、HotpotQA和MuSiQue三个数据集上实现了当前最优的零样本Recall@5与F1分数，推动了非参数化知识融合的发展，提升了证据检索的质量与效率。
原文摘要 · Abstract (English)
Retrieval Augmented Generation (RAG) has become the standard approach for equipping Large Language Models (LLMs) with up-to-date knowledge. However, standard RAG, relying on independent passage retrieval, often fails to capture the interconnected nature of information required for complex, multi-hop reasoning. While structured RAG methods attempt to address this using knowledge graphs built from triples, we argue that the inherent context loss of triples (context collapse) limits the fidelity of the knowledge representation. We introduce PropRAG, a novel RAG framework that shifts from triples to context-rich propositions and introduces an efficient, LLM-free online beam search over proposition paths to discover multi-step reasoning chains. By coupling a higher-fidelity knowledge representation with explicit path discovery, PropRAG achieves state-of-the-art zero-shot Recall@5 and F1 scores on 2Wiki, HotpotQA, and MuSiQue, advancing non-parametric knowledge integration by improving evidence retrieval through richer representation and efficient reasoning path discovery.
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。