PLOP is a cost-based optimizer that finds optimal placements for semantic LLM operators in hybrid query plans via dynamic programming, delivering up to 1.5x speedup and 4.29x cost reduction on 44 benchmark queries while preserving accuracy.
hub
CoRR abs/2505.14661(2025)
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
The authors define a taxonomy for LLM-enhanced relational operators categorized into Select, Match, Impute, Cluster and Order, and release LROBench to evaluate single and multi-operator queries on semantic database processing.
New Text-to-Big SQL metrics show that LLM agents must balance accuracy with cost and speed at scale, where GPT-4o trades some accuracy for up to 12x speedup and GPT-5.2 proves more cost-effective than Gemini 3 Pro on large inputs.
CADENZA introduces TxRA and dual planners to compile semantic operator intents into optimized task DAGs, claiming large gains in quality, latency, and cost on SemBench.
SCOPE is a new optimization method that uses per-query estimates and confidence bounds to select cost-efficient LLM combinations for compound AI systems under quality constraints, with claimed theoretical guarantees and up to 20x lower search cost than baselines on data tasks.
SEMA-SQL automates natural language to efficient hybrid queries combining relational algebra with LLM semantic operations via a new Hybrid Relational Algebra abstraction.
AADvark extends agent-aided CAD design to dynamic 3D assemblies with movable parts by integrating constraint solvers and visual feedback to create a verification signal for the agent.
HoldUp uses LLM-guided clustering to provide holistic dataset context for semantic operators, yielding up to 33% higher classification accuracy and 30% higher scoring accuracy than row-by-row LLM processing across 15 datasets.
CADENZA demonstrates an optimizer that breaks semantic query intents into alternative plans, selects implementations per step, and optimizes under user preferences via a web interface.
CAMI frames multi-index construction for semantic retrieval as a budgeted multi-objective portfolio problem and uses agent-guided search plus confidence-aware pruning to find high-recall configurations with reduced evaluation cost.
Blue DIL is a new architecture that unifies structured enterprise data, LLM world knowledge, and personal context through declarative query plans and agents for multi-source multi-modal applications.
Lightweight proxy models deliver over 100x cost and latency savings for semantic AI queries in databases with accuracy preserved or improved on benchmarks up to 10M rows.
SPEAR proposes structured prompt views, runtime adaptive refinement, and policy rules to make prompts first-class, versioned, and evolvable components in complex LLM applications.
Query-centric AQP and proxy-model strategies reduce expensive model calls by 60-90% with under 10% error on TPC-DS and LLM tasks.
Quantized open-weight LMs on consumer hardware match closed-source API accuracy for LM-enhanced relational operators while delivering 390x lower cost and 3.8x lower latency in the BlendSQL framework.
citing papers explorer
-
Making Prompts First-Class Citizens for Adaptive LLM Pipelines
SPEAR proposes structured prompt views, runtime adaptive refinement, and policy rules to make prompts first-class, versioned, and evolvable components in complex LLM applications.