EUVIMEDEUVIMED entdecken
Crossref

Skyline Retrieval meets Set-Cover Chunk Merging: A Cost-Effective RAG-Sketch for Long-Context LLM QA

Xinyi Zhu, Haoyang Li, Yongqi Zhang, Lei Chen

Proceedings of the ACM on Management of Data · 18.05.2026 · 4 (3) · 1-27

DOI: 10.1145/3802111 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 18.05.2026. Verfasst von Xinyi Zhu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 75 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large Language Model (LLM) question answering (QA) is essential for various real-world applications. As the demand for LLMs in domain-specific, up-to-date, and private scenarios increases, equipping them with large external corpus for QA, referred to long-context LLM QA, becomes critical. However, existing methods struggle to balance the comprehensive retrieval of scattered information required for accurate QA with the high token costs of long-context processing. We identify two major causes of this bottleneck: (1) limited retrieval coverage under complex queries and large input scales, and (2) repeated document access enforced by rigid query-by-query processing. In this paper, we introduce a cost-effective Retrieval-Augmented Generation Sketch (RAG-Sketch) for long-context LLM QA. To enable more thorough information retrieval without exhaustive context traversal, we propose a new skyline retrieval module incorporating query decomposition into a pre-defined schema. This approach retrieves Pareto optimal chunks by jointly considering semantic similarity and the presence of key information within the decomposed queries. Based on retrieved chunks, we formally define a set cover chunk merging optimization problem and proposes a greedy algorithm with theoretical guarantees that effectively reduces redundant access. Our experiments on widely used long-context QA benchmarks demonstrate that RAG-Sketch improves prediction accuracy by 24.5% while reducing token costs by 58.5% compared with the state of the art.

Zitieren

APA

Zhu, X., Li, H., Zhang, Y., & Chen, L. (2026). Skyline Retrieval meets Set-Cover Chunk Merging: A Cost-Effective RAG-Sketch for Long-Context LLM QA. Proceedings of the ACM on Management of Data, 4(3), 1-27. https://doi.org/10.1145/3802111

Vancouver

Zhu X, Li H, Zhang Y, Chen L. Skyline Retrieval meets Set-Cover Chunk Merging: A Cost-Effective RAG-Sketch for Long-Context LLM QA. Proceedings of the ACM on Management of Data. 2026;4(3):1-27. doi:10.1145/3802111

BibTeX
@article{Zhu2026,
  author = {Zhu, Xinyi and Li, Haoyang and Zhang, Yongqi and Chen, Lei},
  title = {Skyline Retrieval meets Set-Cover Chunk Merging: A Cost-Effective RAG-Sketch for Long-Context LLM QA},
  journal = {Proceedings of the ACM on Management of Data},
  year = {2026},
  volume = {4},
  number = {3},
  pages = {1--27},
  doi = {10.1145/3802111}
}
Kostenlos starten →