根据查询复杂度动态调整检索路径，平衡准确率与效率。
Adaptive ToR: Complexity-Aware Tree-Based Retrieval for Pareto-Optimal Multi-Intent NLU
- 按查询复杂度选择单步或分层检索路径，智能分配资源。
- 相比固定深度方法，准确率提升9.7%，延迟降低37.6%。
- 适合需要高效多意图理解的工业级NLU系统部署。
多意图自然语言理解要求检索系统同时具备高准确率和计算高效性。现有方法或采用统一单步检索牺牲召回率，或使用固定深度分层分解引入过量延迟。本文提出自适应树形检索（Adaptive ToR），一种基于查询复杂度动态配置检索拓扑的架构。系统包含四部分：(1) 查询树分类器通过加权语言信号计算查询复杂度指数，决定路由至快速单步路径或自适应深度分层路径；(2) 基于树的检索模块递归分解复杂查询为聚焦子查询，按预测复杂度校准；(3) 自适应剪枝模块采用两阶段过滤，结合定量相似性门控与语义相关性评估，抑制节点指数增长；(4) 检索重排序层采用去重优先流水线与全局大模型重评分，保障生产效率。在NLU++基准测试（涵盖银行与酒店领域共2,693个多意图查询）上，取得29.07%子集准确率和71.79%微F1，较固定深度基线相对提升9.7%，延迟降低37.6%，大模型调用减少43.0%，令牌消耗下降9.8%。深度分析显示，26.92%的查询在三秒内完成（平均2.45秒），单步路由（d=0）实现37.9%子集准确率、74.8%微F1，而令牌消耗随深度增加达4.9倍，验证了复杂度感知资源分配的有效性，实现了准确率、延迟与计算效率的帕累托最优平衡。
原文摘要 · Abstract (English)
Multi-intent natural language understanding requires retrieval systems that simultaneously achieve high accuracy and computational efficiency, yet existing approaches apply either uniform single-step retrieval that compromises recall or fixed-depth hierarchical decomposition that introduces excessive latency regardless of query complexity. This paper proposes Adaptive Tree-of-Retrieval (Adaptive ToR), a complexity-aware retrieval architecture that dynamically configures retrieval topology based on query characteristics. The system integrates four components: (1) a Query Tree Classifier computing a Query Complexity Index from weighted linguistic signals to route queries to either a rapid single-step path or an adaptive-depth hierarchical path; (2) a Tree-Based Retrieval module that recursively decomposes complex queries into focused sub-queries calibrated to predicted complexity; (3) an Adaptive Pruning Module employing two-stage filtering combining quantitative similarity gating with semantic relevance evaluation to suppress exponential node growth; and (4) a Retrieval Reranking Layer featuring a deduplicator-first pipeline and global LLM rescoring for production efficiency. Evaluation on the NLU++ benchmark (2,693 multi-intent queries across Banking and Hotel domains) yields 29.07% Subset Accuracy and 71.79% Micro-F1, a 9.7% relative improvement over fixed-depth baselines, while reducing latency by 37.6%, LLM invocations by 43.0%, and token consumption by 9.8%. Depth-wise analysis reveals that 26.92% of queries resolve within three seconds (2.45s mean latency) via single-step routing (d=0: 37.9% Subset Accuracy, 74.8% Micro-F1), while token consumption scales by 4.9x across depths, validating complexity-aware resource allocation and establishing Pareto-optimal balance across accuracy, latency, and computational efficiency.
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。