链式推理特征转换的进化演示优化
Evolving Demonstration Optimization for Chain-of-Thought Feature Transformation
AI总结：
本文提出一种通过进化轨迹经验优化LLM驱动的特征转换方法，提升转换多样性与下游任务性能。
摘要：
特征转换（FT）是一种核心的数据导向AI任务，通过提高特征空间的质量来提升下游预测性能。然而，发现有效的转换仍然具有挑战性，因为特征-运算符组合的大量空间使得问题复杂化。现有解决方案依赖于离散搜索或潜在生成，但它们经常受到样本效率低、无效候选和生成冗余且覆盖范围有限的限制。大型语言模型（LLMs）提供了生成有效转换的强大先验知识，但当前基于LLM的FT方法通常依赖于静态演示，导致转换结果的多样性有限、输出冗余且与下游目标对齐弱。我们提出一个框架，通过在闭环中进化轨迹级经验来优化上下文数据以驱动LLM的FT。从强化学习探索的高性能特征传输序列开始，我们构建并持续更新一个下游任务验证的转换轨迹经验库，并使用具有多样性的选择器来形成上下文，同时结合链式推理和引导转换特征生成以实现更高的性能。在多样化的表格基准测试中，我们的方法优于经典和基于LLM的基线方法，并且比单次生成更稳定。该框架在API基于和开源LLM之间具有泛化能力，并且在下游评估器中保持稳健。
英文摘要：
Feature Transformation (FT) is a core data-centric AI task that improves feature space quality to advance downstream predictive performance. However, discovering effective transformations remains challenging due to the large space of feature-operator combinations. Existing solutions rely on discrete search or latent generation, but they are frequently limited by sample inefficiency, invalid candidates, and redundant generations with limited coverage. Large Language Models (LLMs) offer strong priors for producing valid transformations, but current LLM-based FT methods typically rely on static demonstrations, resulting in limited diversity, redundant outputs, and weak alignment with downstream objectives. We propose a framework that optimizes context data for LLM-driven FT by evolving trajectory-level experiences in a closed loop. Starting from high-performing feature transportation sequences explored by reinforcement learning, we construct and continuously update an experience library of downstream task-verified transformation trajectories, and use a diversity-aware selector to form contexts along with a chain-of-thought and guide transformed feature generation toward higher performance. Experiments on diverse tabular benchmarks show that our method outperforms classical and LLM-based baselines and is more stable than one-shot generation. The framework generalizes across API-based and open-source LLMs and remains robust across downstream evaluators.
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。
