SemPipes -- Optimizable Semantic Data Operators for Tabular Machine Learning Pipelines

TL;DR

SemPipes introduces a declarative framework that leverages large language models to synthesize and optimize data transformation operators in tabular machine learning pipelines, improving performance and reducing complexity.

Contribution

It presents SemPipes, a novel system integrating LLM-powered semantic operators into pipelines, enabling automatic optimization and code synthesis based on data and context.

Findings

Semantic operators improve predictive accuracy.

Pipeline complexity is reduced.

Performance gains are consistent across tasks.

Abstract

Real-world machine learning on tabular data relies on complex data preparation pipelines for prediction, data integration, augmentation, and debugging. Designing these pipelines requires substantial domain expertise and engineering effort, motivating the question of how large language models (LLMs) can support tabular ML through code synthesis. We introduce SemPipes, a novel declarative programming model that integrates LLM-powered semantic data operators into tabular ML pipelines. Semantic operators specify data transformations in natural language while delegating execution to a runtime system. During training, SemPipes synthesizes custom operator implementations based on data characteristics, operator instructions, and pipeline context. This design enables the automatic optimization of data operations in a pipeline via LLM-based code synthesis guided by evolutionary search. We evaluate SemPipes across diverse tabular ML tasks and show that semantic operators substantially improve end-to-end predictive performance for both expert-designed and agent-generated pipelines, while reducing pipeline complexity. We implement SemPipes in Python and release it at https://github.com/deem-data/sempipes/tree/v1.