# Semantic Views: Certified Reuse of LLM Labels Across Semantic Queries

arXiv: https://arxiv.org/abs/2610.12768 · HTML: https://mlsanity.com/paper/2610.12768/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 65 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Builds on (most cited first, 30 of 35)

- [Prediction-Powered Inference](https://mlsanity.com/paper/2301.09633/) (2023)
- [A Declarative System for Optimizing AI Workloads](https://mlsanity.com/paper/2405.14696/) (2024)
- [Semantic Operators: A Declarative Model for Rich, AI-based Data Processing](https://mlsanity.com/paper/2407.11418/) (2024)
- [Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First](https://mlsanity.com/paper/2509.00997/) (2025)
- [Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation](https://mlsanity.com/paper/2406.04291/) (2024)
- [Optimizing LLM Queries in Relational Data Analytics Workloads](https://mlsanity.com/paper/2403.05821/) (2024)
- [GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching](https://mlsanity.com/paper/2411.05276/) (2024)
- [UQE: A Query Engine for Unstructured Databases](https://mlsanity.com/paper/2407.09522/) (2024)
- [vCache: Verified Semantic Prompt Caching](https://mlsanity.com/paper/2502.03771/) (2025)
- [Approximate Selection with Guarantees using Proxies](https://mlsanity.com/paper/2004.00827/) (2020)
- [Beyond Quacking: Deep Integration of Language Models and RAG into DuckDB](https://mlsanity.com/paper/2504.01157/) (2025)
- [Abacus: A Cost-Based Optimizer for Semantic Operator Systems](https://mlsanity.com/paper/2505.14661/) (2025)
- [Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptation](https://mlsanity.com/paper/2508.07675/) (2025)
- [Semantic Indexes for Machine Learning-based Queries over Unstructured Data](https://mlsanity.com/paper/2009.04540/) (2020)
- [Accelerating Approximate Aggregation Queries with Expensive Predicates](https://mlsanity.com/paper/2108.06313/) (2021)
- [QUEST: Query Optimization in Unstructured Document Analysis](https://mlsanity.com/paper/2507.06515/) (2025)
- [SemBench: A Benchmark for Semantic Query Processing Engines](https://mlsanity.com/paper/2511.01716/) (2025)
- [Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimization](https://mlsanity.com/paper/2511.19830/) (2025)
- [Task Cascades for Efficient Unstructured Data Processing](https://mlsanity.com/paper/2601.05536/) (2026)
- [Larch: Learned Query Optimization for Semantic Predicates](https://mlsanity.com/paper/2606.07923/) (2026)
- [ScaleDoc: Scaling LLM-based Predicates over Large Document Collections](https://mlsanity.com/paper/2509.12610/) (2025)
- [The Stretto Execution Engine for LLM-Augmented Data Systems](https://mlsanity.com/paper/2602.04430/) (2026)
- [Sema: A High-performance System for LLM-based Semantic Query Processing](https://mlsanity.com/paper/2603.11622/) (2026)
- [Streaming Model Cascades for Semantic SQL](https://mlsanity.com/paper/2604.00660/) (2026)
- [SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models](https://mlsanity.com/paper/2604.23477/) (2026)
- [PLOP: Cost-Based Placement of Semantic Operators in Hybrid Query Plans](https://mlsanity.com/paper/2604.09944/) (2026)
- [Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase Method](https://mlsanity.com/paper/2606.08090/) (2026)
- [CADENZA: Compiling Natural-Language Intent into Task-Specific Operator DAGs for Semantic Query Processing](https://mlsanity.com/paper/2606.29151/) (2026)
- [Kalypso: Relational LLM Serving](https://mlsanity.com/paper/2607.23815/) (2026)
- [From Interpretation to Compilation: A Compilation-Based Execution Engine for Semantic Operator Systems](https://mlsanity.com/paper/2608.06677/) (2026)

## Abstract (arXiv)

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 little, and all of them discard the oracle's labels when the query ends. We present SemViews, a certified semantic filter that orders tuples by signals that cost no oracle calls (the labels that earlier queries left behind as semantic views, a local embedding, and a helper model's score), refines that order with labels it must pay for anyway, and certifies its answer with fresh stratified oracle samples. The answer meets user precision and recall targets with probability at least 1-δ for every workload and every catalog, so a stale or misleading view can cost oracle calls but never accuracy. On four workloads replayed against 725,000 recorded oracle labels, SemViews meets both targets on 99.63% of queries and saves 28%-45% of the oracle calls, whereas the only prior method in our study with the same guarantee needs 1.32x-1.71x as many calls. When a question returns in different words, views cut its calls by a further 27%-36%, with both targets met on at least 99.8% of such queries; similarity caches and entailment-based reuse meet them on only 17%-47%.