EUVIMEDEUVIMED entdecken
Crossref

Task Cascades for Efficient Unstructured Data Processing

Shreya Shankar, Sepanta Zeighami, Aditya Parameswaran

Proceedings of the ACM on Management of Data · 02.04.2026 · 4 (1) · 1-26

DOI: 10.1145/3786702 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 07.04.2026. Verfasst von Shreya Shankar und 2 weiteren Autor:innen. Die Arbeit nennt 70 Literaturangaben. Gefördert von: NSF (National Science Foundation).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modern database systems allow users to query or process unstructured text or document columns using LLM-powered functions. Users can express an operation in natural language (e.g., ''identify if this review mentions billing issues''), with the system executing the operation on each document, in a row-by-row fashion. One way to reduce cost on a batch of documents is to employ the model cascade framework: a cheap proxy model processes each document, and only uncertain cases are escalated to a more accurate, expensive oracle. However, model cascades miss important optimization opportunities; for example, often only part of a document is needed to answer a query, or other related, but simpler operations (e.g., ''is the review sentiment negative?'', ''does the review mention money?'') can be handled by cheap models more effectively than the original operation, while still being correlated with it. We introduce the task cascades framework, which generalizes model cascades by varying not just the model, but also the document portion and operation at each stage. Our framework uses an LLM agent to generate simplified, decomposed, or otherwise related operations and selects the most relevant document portions, constructing hundreds of candidate tasks from which it assembles a task cascade. We show that optimal cascade selection is intractable via reduction from Minimum Sum Set Cover, but our iterative approach constructs effective cascades. We also provide an extension that offers statistical accuracy guarantees: the resulting cascade meets a user-defined accuracy target (with respect to the oracle) up to a bounded failure probability. Across eight real-world document processing tasks at a 90% target accuracy, task cascades reduce end-to-end cost by an average of 36% compared to model cascades, at a production scale.

Förderung

  • NSF (National Science Foundation)

Zitieren

APA

Shankar, S., Zeighami, S., & Parameswaran, A. (2026). Task Cascades for Efficient Unstructured Data Processing. Proceedings of the ACM on Management of Data, 4(1), 1-26. https://doi.org/10.1145/3786702

Vancouver

Shankar S, Zeighami S, Parameswaran A. Task Cascades for Efficient Unstructured Data Processing. Proceedings of the ACM on Management of Data. 2026;4(1):1-26. doi:10.1145/3786702

BibTeX
@article{Shankar2026,
  author = {Shankar, Shreya and Zeighami, Sepanta and Parameswaran, Aditya},
  title = {Task Cascades for Efficient Unstructured Data Processing},
  journal = {Proceedings of the ACM on Management of Data},
  year = {2026},
  volume = {4},
  number = {1},
  pages = {1--26},
  doi = {10.1145/3786702}
}
Kostenlos starten →