不训练也不建图，用桥梁信息精准筛选多跳问答候选答案
BridgeRAG: Training-Free Bridge-Conditioned Retrieval for Multi-Hop Question Answering
- 用三元组评分器根据桥接证据动态评估候选答案相关性
- 在三个标准数据集上达到最优无训练检索效果，最高提升6.8个百分点
- 适合需要高精度多跳推理但无法训练模型的场景
多跳检索并非单一阶段的相关性判断：后一跳证据应基于已获取的桥接证据进行效用评估，而非仅与原始问题相似。我们提出BridgeRAG，一种无需训练、无需图结构的多跳问答检索方法，通过三元组评分函数s(q,b,c)对（问题, 桥接证据, 候选答案）进行评估。BridgeRAG将覆盖范围与评分分离：双重实体近似最近邻扩展扩大第二跳候选池，而桥接条件化的大型语言模型裁判在不依赖离线图或命题索引的情况下识别活跃推理链。在四项控制实验中，该条件信号表现出：(i)选择性：平行链查询上提升2.55个百分点（p<0.001），单链子类型几乎无增益；(ii)不可替代性：用生成的SVO查询文本替换检索段落使R@5下降2.1个百分点，甚至低于最低相似度段落；(iii)可预测性：桥接向量与增益相关性显著（斯皮尔曼等级相关系数rho=0.104，p<0.001）；(iv)机制精确性：桥接条件引发有效重排序（平行链翻转胜率18.7%对比单链0.6%）。结合轻量级覆盖扩展与百分位分数融合，BridgeRAG在所有三个标准多跳问答基准上以匹配评估条件下实现最佳公开无训练结果：MuSiQue上0.8146（较PropRAG+3.1pp，较HippoRAG2+6.8pp），2WikiMultiHopQA上0.9527（较PropRAG+1.2pp），HotpotQA上0.9875（较PropRAG+1.35pp）。
原文摘要 · Abstract (English)
Multi-hop retrieval is not a single-step relevance problem: later-hop evidence should be ranked by its utility conditioned on retrieved bridge evidence, not by similarity to the original query alone. We present BridgeRAG, a training-free, graph-free retrieval method for retrieval-augmented generation (RAG) over multi-hop questions that operationalizes this view with a tripartite scorer s(q,b,c) over (question, bridge, candidate). BridgeRAG separates coverage from scoring: dual-entity ANN expansion broadens the second-hop candidate pool, while a bridge-conditioned LLM judge identifies the active reasoning chain among competing candidates without any offline graph or proposition index. Across four controlled experiments we show that this conditioning signal is (i) selective: +2.55pp on parallel-chain queries (p<0.001) vs. ~0 on single-chain subtypes; (ii) irreplaceable: substituting the retrieved passage with generated SVO query text reduces R@5 by 2.1pp, performing worse than even the lowest-SVO-similarity pool passage; (iii) predictable: cos(b,g2) correlates with per-query gain (Spearman rho=0.104, p<0.001); and (iv) mechanistically precise: bridge conditioning causes productive re-rankings (18.7% flip-win rate on parallel-chain vs. 0.6% on single-chain), not merely more churn. Combined with lightweight coverage expansion and percentile-rank score fusion, BridgeRAG achieves the best published training-free R@5 under matched benchmark evaluation on all three standard MHQA benchmarks without a graph database or any training: 0.8146 on MuSiQue (+3.1pp vs. PropRAG, +6.8pp vs. HippoRAG2), 0.9527 on 2WikiMultiHopQA (+1.2pp vs. PropRAG), and 0.9875 on HotpotQA (+1.35pp vs. PropRAG).
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。