EUVIMEDEUVIMED entdecken
Crossref

BAT: Target-Instance-Free Data Preparation Synthesis via LLM-Driven Tree Search

Congcong Ge, Yachuan Liu, Yixuan Tang, Yifan Zhu, Yaofeng Tu, Yunjun Gao

Proceedings of the ACM on Management of Data · 18.05.2026 · 4 (3) · 1-25

DOI: 10.1145/3802020 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 18.05.2026. Verfasst von Congcong Ge und 5 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In real-world scenarios, a pervasive requirement for automatic data preparation (ADP) is to transform diverse relational tables from different sources into a specified target table. Previous methods rely on labor-intensive supervision signals or access permissions to target table data, limiting their usage in commercial systems. To tackle these challenges, we propose BAT, the first end-to-end ADP framework. It enables the synthesis of training-free data preparation pipelines without requiring any instances from target tables. BAT is formulated as an open-source large language model (LLM) driven tree-structured search problem.It consists of three pivot components, i.e., a data preparation action sandbox (DPAS), a fundamental pipeline generator (fFPG), and an execution-aware pipeline optimizer (EPO). We first introduce DPAS, a lightweight action sandbox, to navigate the search-based data preparation pipeline generation process. The design of DPAS circumvents exploration of infeasible pipelines. Then, we present FPG, an LLM-driven Monte Carlo tree search process, to incrementally generate executable DP pipelines within the constraints of the predefined action sandbox. Furthermore, we propose EPO, which invokes pipeline execution results from sources to targets to evaluate the reliability of the generated pipelines in FPG. In this way, unreasonable pipelines are eliminated, thus facilitating the search process from both efficiency and effectiveness perspectives. Extensive experiments on real-world datasets show that BAT significantly outperforms 5 SOTA competitors, achieving at least 8.74% improvements in the end-to-end data preparation pipeline execution accuracy.

Zitieren

APA

Ge, C., Liu, Y., Tang, Y., Zhu, Y., Tu, Y., & Gao, Y. (2026). BAT: Target-Instance-Free Data Preparation Synthesis via LLM-Driven Tree Search. Proceedings of the ACM on Management of Data, 4(3), 1-25. https://doi.org/10.1145/3802020

Vancouver

Ge C, Liu Y, Tang Y, Zhu Y, Tu Y, Gao Y. BAT: Target-Instance-Free Data Preparation Synthesis via LLM-Driven Tree Search. Proceedings of the ACM on Management of Data. 2026;4(3):1-25. doi:10.1145/3802020

BibTeX
@article{Ge2026,
  author = {Ge, Congcong and Liu, Yachuan and Tang, Yixuan and Zhu, Yifan and Tu, Yaofeng and Gao, Yunjun},
  title = {BAT: Target-Instance-Free Data Preparation Synthesis via LLM-Driven Tree Search},
  journal = {Proceedings of the ACM on Management of Data},
  year = {2026},
  volume = {4},
  number = {3},
  pages = {1--25},
  doi = {10.1145/3802020}
}
Kostenlos starten →