EUVIMEDEUVIMED entdecken
Crossref

Evergreen: Efficient Claim Verification for Semantic Aggregates

Alexander W. Lee, Benjamin Han, Shayak Sen, Sam Yeom, Uğur Çetintemel, Anupam Datta

Proceedings of the VLDB Endowment · 01.09.2026 · 20 (1) · 16-30

DOI: 10.14778/3845598.3845600 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 06.11.2026. Verfasst von Alexander W. Lee und 5 weiteren Autor:innen. Die Arbeit nennt 92 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With recent semantic query processing engines, semantic aggregation has become a primitive operator, enabling the reduction of a relation into a natural language aggregate using an LLM. However, the resulting semantic aggregate may contain claims that are not grounded in the underlying relation. Verifying such claims is challenging: they often involve quantifiers, groupings, and comparisons over relations that far exceed LLM context windows and require an expensive combination of semantic and symbolic processing. We present Evergreen, a system that recasts claim verification as a semantic query processing task with tailored optimizations and provenance capture. Evergreen compiles each claim into a declarative semantic verification query that can execute on the same query engine used to produce the aggregate. To reduce cost, Evergreen avoids unnecessary LLM calls through verification-aware optimizations, including early stopping, relevance sorting, and estimation with confidence sequences, as well as general-purpose optimizations for semantic queries, such as operator fusion, similarity filtering, and prompt caching. Each verdict is accompanied by citations that identify a minimal set of tuples justifying the result, with semantics based on semiring provenance for first-order logic. On a benchmark of production-inspired workloads over restaurant review and customer support datasets, Evergreen's optimized configurations occupy the entire cost-quality Pareto frontier. With a strong LLM, Evergreen preserves verification quality at an F1 of 0.94 while reducing cost by 3.1× relative to unoptimized verification; with a substantially weaker LLM, it surpasses the strongest external baseline's F1 (0.87 vs. 0.83) at 7.0× lower cost.

Zitieren

APA

Lee, A. W., Han, B., Sen, S., Yeom, S., Çetintemel, U., & Datta, A. (2026). Evergreen: Efficient Claim Verification for Semantic Aggregates. Proceedings of the VLDB Endowment, 20(1), 16-30. https://doi.org/10.14778/3845598.3845600

Vancouver

Lee AW, Han B, Sen S, Yeom S, Çetintemel U, Datta A. Evergreen: Efficient Claim Verification for Semantic Aggregates. Proceedings of the VLDB Endowment. 2026;20(1):16-30. doi:10.14778/3845598.3845600

BibTeX
@article{Lee2026,
  author = {Lee, Alexander W. and Han, Benjamin and Sen, Shayak and Yeom, Sam and Çetintemel, Uğur and Datta, Anupam},
  title = {Evergreen: Efficient Claim Verification for Semantic Aggregates},
  journal = {Proceedings of the VLDB Endowment},
  year = {2026},
  volume = {20},
  number = {1},
  pages = {16--30},
  doi = {10.14778/3845598.3845600}
}
Kostenlos starten →