Skip to content
Preprint

Prune First, Decide Fast: Scalable Semantic Query Processing with JEVDB

Oct 2026 · 3 citations · ⚡ 1 influential · 39 references
Computer Science

TL;DR

JEVDB is presented, a scalable semantic database system that uses fast, typed decision models for semantic filters, joins, classification, and ranking, while selectively escalating uncertain cases to generative LLMs.

Abstract

Semantic database systems extend SQL with foundation-model inference over unstructured data, but current engines rely heavily on autoregressive LLMs for discrete relational decisions, creating high latency and monetary cost. We present JEVDB, a scalable semantic database system that uses fast, typed decision models for semantic filters, joins, classification, and ranking, while selectively escalating uncertain cases to generative LLMs. To reduce semantic-join work, JEVDB combines exact Yannakakis-style semijoin reduction over relational structure with Semantic Bloom Filters (SBFs), which use registered necessary conditions to screen candidates across latent semantic edges. We evaluate JEVDB on SemBench and Shelob, a TPC-DS-derived semantic-join workload. On SemBench, JEVDB-Flash achieves the lowest latency on all 21 evaluated queries and the lowest cost on 19, while maintaining competitive answer quality. On Shelob, where joins scale to 540K candidate pairs, JEVDB completes all queries with 95.7%-97.5% mean F1. SBF screening removes 87.4% of candidate pairs before semantic evaluation, and reusable condition-index scoring further reduces reasoning-model escalations by 55.2%. An interactive query simulator, source code, and benchmarks are available at https://jevdb.org.

View source

Similar papers

Book Open access Nov 2026

SERA: Evaluating LLM-based SEmantic RAnking over Structured Tables

LLM-based data systems are moving beyond text-to-SQL toward semantic query processing, where natural language requests are executed through operators that combine relational processing with LLM-driven inference. A central operator in this setting is SemanticRank, or semantic top-k: given a user intent and a set of rela...

E. Lenzi, D. Martinenghi, Paolo Papotti et al. · 0 citations
Open access 2026

ACMO: An Adaptive Cost Modeling and Optimization Framework for Schema-Heterogeneous NoSQL Document Databases

ACMO, the Adaptive Cost Modeling and Optimization framework, is introduced, which estimates query costs on MongoDB-style document collections without requiring query execution traces or a running database engine, relying instead on document structure and field-level statistics.

R. Porchezhian, Roshini Pininti, A. Sudha et al. · 0 citations
Preprint Oct 2026

NousDB - A Fast Query Engine for Semantic Analytics

This work presents NousDB, a high-performance semantic analytics engine built on Apache DataFusion, and proposes an extended relational algebra with three semantic operators and formal algebraic properties that enable principled query rewriting and cross-operator optimization.

Christos Tsapelas, Georgia Koutrika, Y. Ioannidis · 0 citations
Book Open access Nov 2026

Preserving LLM Output Distributions for Probabilistic Query Evaluation

Language models can be used to augment databases; typically, when this is done, their top prediction is used while the uncertainty in this prediction is ignored. We propose a framework that preserves output distributions from language model predictions and uses them to evaluate SQL queries probabilistically. First, a l...

Angelo Saadeh, Pierre Senellart · 0 citations
#small language model Open access Oct 2026

Commerce core: Low-Budget Multitask Adaptation for Structured E-Commerce Queries

Small language models offer a practical way to convert shopping queries into ex-ecutable constraints, but partial extraction accuracy can obscure whether the com-plete request is represented correctly. We study CommerceCore, a Qwen3-1.7B model adapted with QLoRA on 2,130 examples spanning entity segmentation, query con...

Mukherjee Arghya · 0 citations
#artificial intelligence Preprint Oct 2026

Semantic Views: Certified Reuse of LLM Labels Across Semantic Queries

Semantic query engines evaluate natural-language filters with a large language model, and every evaluation is a costly oracle call. Optimizers that reduce these calls face a dilemma: cascades that trust a cheap proxy miss their precision and recall targets on many queries, methods with finite-sample guarantees save lit...

Oktie Hassanzadeh, D. Subramanian · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.