发表机构
Jinan University; The Hong Kong Polytechnic University; City University of Macau; Jilin University; Beihang University（暨南大学; 香港理工大学; 澳门城市大学; 吉林大学; 北京航空航天大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对上下文学习文本到SQL流程的模块，量化各范式的成本-准确性贡献，发现执行反馈优化性价比最高，提出感知成本的分层指南并可迁移至其他主干模型。
AI 中文摘要
上下文学习（ICL）文本到SQL的最新进展，通过围绕基础生成器构建日益复杂的流程，大幅提升了公共基准上的执行准确率，但现有研究通常仅报告聚合的端到端准确率，未量化各个设计选择的边际准确性-成本贡献。因此，提供统一的范式级成本-准确性量化仍是理解和配置现代文本到SQL的关键挑战。为解决该问题，我们在单一受控实现下，针对ICL文本到SQL流程的五个重复模块实例化17种范式级配置，并在四种覆盖不同能力水平和推理风格的主干模型上，归因每种范式的边际贡献及产生的成本。我们的分析显示，执行反馈优化是唯一在成本持续较低时仍能普遍发挥作用的范式，而大多数其他模块仅在依赖主干模型的条件下才有用。Token计数表明，输入需求与流程结构的关联更紧密，而输出需求对主干模型的生成行为更敏感。跨模块分析进一步显示，堆叠（stacking）可提升大多数主干模型的准确率，不过增益的组合方式随主干模型能力变化。我们还发现，固定预算通常更适合用于在中端主干模型上构建更复杂的流程，而非升级为使用精简流程的前沿模型。这些发现提炼为可操作的、感知成本的分层指南，可迁移到另外五种主干模型，无需进行逐范式搜索。
英文摘要
Recent advances in in-context learning (ICL) text-to-SQL have substantially improved execution accuracy on public benchmarks by assembling increasingly elaborate pipelines around the base generator, yet existing studies typically report aggregate end-to-end accuracy, without quantifying the marginal accuracy-cost contribution of individual design choices. Consequently, providing a unified, paradigm-level cost-accuracy quantification remains a critical challenge for understanding and configuring modern text-to-SQL. To address this, we instantiate 17 paradigm-level configurations across five recurring modules of the ICL text-to-SQL pipeline under a single controlled implementation, and attribute each paradigm's marginal contribution and incurred cost across all four backbones spanning diverse capability levels and reasoning styles. Our analysis reveals that execution-feedback refinement is the only paradigm whose benefit holds universally at consistently low cost, while most other modules help only under backbone-dependent conditions. Token accounting shows that input demand is more closely tied to pipeline structure, whereas output demand is more sensitive to backbone generation behavior. Cross-module analysis further shows that stacking improves accuracy on most backbones, although how the gains compose varies with backbone capability. We also find that a fixed budget is often better spent engineering a more elaborate pipeline over a mid-tier backbone than upgrading to a frontier model with a lean pipeline. These findings distill into an actionable, cost-aware tiered guideline that transfers to five additional backbones without per-paradigm search.
