用自然语言生成复杂数据流程，自动配置步骤和连接关系。
Classifier-Augmented Generation for Structured Workflow Prediction
- 结合分类器与提示工程，分解语句精准预测流程节点。
- 在多个任务上优于单次提示和智能体基线，减少30%以上令牌消耗。
- 适合需要快速构建数据流水线的开发者或数据工程师使用。
ETL工具如IBM DataStage允许用户通过可视化方式组装复杂的数据工作流，但配置各个阶段及其属性仍耗时且需深入掌握工具知识。本文提出一种系统，可将自然语言描述自动转化为可执行的工作流，实现流程结构与详细配置的联合预测。核心是分类器增强生成（CAG）方法，通过话语分解、分类器辅助和阶段特定的少样本提示，提升阶段预测准确性。随后利用边预测构建非线性工作流，并从子语句上下文中推断阶段属性。与强基线相比，CAG在准确率和效率上均表现更优，同时显著降低令牌使用量。该架构模块化、可解释，支持端到端工作流生成，包含稳健的验证步骤。据我们所知，这是首个对阶段预测、边布局和属性生成进行详尽评估的自然语言驱动ETL创作系统。
原文摘要 · Abstract (English)
ETL (Extract, Transform, Load) tools such as IBM DataStage allow users to visually assemble complex data workflows, but configuring stages and their properties remains time consuming and requires deep tool knowledge. We propose a system that translates natural language descriptions into executable workflows, automatically predicting both the structure and detailed configuration of the flow. At its core lies a Classifier-Augmented Generation (CAG) approach that combines utterance decomposition with a classifier and stage-specific few-shot prompting to produce accurate stage predictions. These stages are then connected into non-linear workflows using edge prediction, and stage properties are inferred from sub-utterance context. We compare CAG against strong single-prompt and agentic baselines, showing improved accuracy and efficiency, while substantially reducing token usage. Our architecture is modular, interpretable, and capable of end-to-end workflow generation, including robust validation steps. To our knowledge, this is the first system with a detailed evaluation across stage prediction, edge layout, and property generation for natural-language-driven ETL authoring.
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。