提出可迁移的双跳问答路由机制，按问题类型自动选择检索策略。
Regime-Conditional Retrieval: Theory and a Transferable Router for Two-Hop QA
- 基于三个定理构建路由规则，根据问题特征判断检索路径。
- 在三个数据集上实现最高5.6个百分点的准确率提升。
- 轻量级设计适合零样本迁移，适用于多跳问答系统优化。
双跳问答检索将问题分为两类：一类是第二跳实体在问题中明确提及（Q主导），另一类是仅在桥接段落中出现（B主导）。本文通过三个定理形式化该划分：(T1) 每个查询的AUC是余弦分离边际的单调函数，六组类型编码器对的R² ≥ 0.90；(T2) 路由由两个表面文本谓词决定，其中P1起决定性作用，P2用于限定B主导情形，该规律在三种编码器和三个数据集上均成立；(T3) 桥接优势依赖于承载关系的句子，而非仅实体名称，移除后性能下降8.6-14.1个百分点（p < 0.001）。基于此理论，提出RegimeRouter——一种轻量级二分类路由器，利用五个直接来自谓词定义的文本特征，在问题仅检索与问题+关系句检索间进行选择。在2WikiMultiHopQA（n = 881，五折交叉拟合）上训练，零样本迁移至MuSiQue和HotpotQA，分别获得+5.6（p < 0.001）、+5.3（p = 0.002）和+1.1（不显著，无损）的R@5提升，且无误引入人工信号。
原文摘要 · Abstract (English)
Two-hop QA retrieval splits queries into two regimes determined by whether the hop-2 entity is explicitly named in the question (Q-dominant) or only in the bridge passage (B-dominant). We formalize this split with three theorems: (T1) per-query AUC is a monotone function of the cosine separation margin, with R^2 >= 0.90 for six of eight type-encoder pairs; (T2) regime is characterized by two surface-text predicates, with P1 decisive for routing and P2 qualifying the B-dominant case, holding across three encoders and three datasets; and (T3) bridge advantage requires the relation-bearing sentence, not entity name alone, with removal causing an 8.6-14.1 pp performance drop (p < 0.001). Building on this theory, we propose RegimeRouter, a lightweight binary router that selects between question-only and question-plus-relation-sentence retrieval using five text features derived directly from the predicate definitions. Trained on 2WikiMultiHopQA (n = 881, 5-fold cross-fitted) and applied zero-shot to MuSiQue and HotpotQA, RegimeRouter achieves +5.6 pp (p < 0.001), +5.3 pp (p = 0.002), and +1.1 pp (non-significant, no-regret) R@5 improvement, respectively, with artifact-driven.
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。