S-Path-RAG：基于语义的最短路径检索增强生成用于多跳知识图谱问答
S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answering
AI总结：
S-Path-RAG通过混合加权k最短路径、束搜索和约束随机游走策略，实现语义感知的多跳知识图谱问答，提升检索效率与生成准确性。
摘要：
我们提出了S-Path-RAG，一种语义感知的最短路径检索增强生成框架，旨在改进大规模知识图谱上的多跳问答。S-Path-RAG摒弃了一次性文本密集检索，采用混合加权k最短、束搜索和约束随机游走策略，学习可微分的路径评分器与对比路径编码器和轻量验证器，并通过交叉注意力将选定路径的潜在表示注入语言模型。系统在迭代的神经-苏格拉底图对话循环中运行，其中语言模型生成的简洁诊断信息被映射到目标图编辑或种子扩展，从而在模型不确定时实现自适应检索。这种组合产生了一种在令牌效率和拓扑感知性方面均优于现有方法的检索机制，同时保留了可解释的路径级追踪用于诊断和干预。我们通过标准多跳KGQA基准测试、消融分析和诊断分析验证了S-Path-RAG。结果表明，与强大的图和LLM基线相比，S-Path-RAG在答案准确性、证据覆盖和端到端效率上均表现出一致的改进。我们进一步分析了语义加权、验证器过滤和迭代更新之间的权衡，并报告了在受限计算和令牌预算下的实际部署建议。
英文摘要：
We present S-Path-RAG, a semantic-aware shortest-path Retrieval-Augmented Generation framework designed to improve multi-hop question answering over large knowledge graphs. S-Path-RAG departs from one-shot, text-heavy retrieval by enumerating bounded-length, semantically weighted candidate paths using a hybrid weighted $k$-shortest, beam, and constrained random-walk strategy, learning a differentiable path scorer together with a contrastive path encoder and lightweight verifier, and injecting a compact soft mixture of selected path latents into a language model via cross-attention. The system runs inside an iterative Neural-Socratic Graph Dialogue loop in which concise diagnostic messages produced by the language model are mapped to targeted graph edits or seed expansions, enabling adaptive retrieval when the model expresses uncertainty. This combination yields a retrieval mechanism that is both token-efficient and topology-aware while preserving interpretable path-level traces for diagnostics and intervention. We validate S-Path-RAG on standard multi-hop KGQA benchmarks and through ablations and diagnostic analyses. The results demonstrate consistent improvements in answer accuracy, evidence coverage, and end-to-end efficiency compared to strong graph- and LLM-based baselines. We further analyze trade-offs between semantic weighting, verifier filtering, and iterative updates, and report practical recommendations for deployment under constrained compute and token budgets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
