PROBE: Learned Proxy-Based Execution for Highly Selective Multimodal Semantic Queries
cs.DB
Submitted: 2026-11-01
Updated: 2026-11-06
License: http://creativecommons.org/licenses/by-sa/4.0/
The gist: Large language models (LLMs) enable semantic queries over unstructured data, but invoking an LLM on every row is prohibitively expensive.
Terminology
Abstract
Large language models (LLMs) enable semantic queries over unstructured data, but invoking an LLM on every row is prohibitively expensive. Proxy-based execution can reduce this ple with the LLM and training a lightweight proxyto label the remaining rows. Nevertheless, in practical scenarios where semantic queries are highly selective, it remainschallenging to identify representative samples foLM budget and to achieve accurate predictions overthe remaining data using the proxy. We present PROBE, a learned proxy-based execution framework for highly selective multimodal semantic queries. PROBE uses selectivity-adaptive sampling to discover rare polightweight proxy on the acquired labels. It thenrefines proxy predictions through residual correction and homogeneity smoothing over a similarity graph. To address sampling bias, PROBE jointly calibrates refined scores usiarate calibration sample, then selectively routescandidates to the LLM by optimizing the tradeoff between estimated F1 and evaluation cost. On queries from SemBench and LRO-Bench with positive rates as low as 2.17x10-5 budget yields a geometric-mean F1 of 0.762,compared with 0.797 for exhaustive LLM evaluation, at a geometric-mean speedup of 4.87x and a maximum speedup of 9.3x.
Sources
- Qwen3-VL Technical Report
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- Gemma 4 Technical Report
- Beyond Linear LLM Invocation: An Efficient and Effective Semantic Filter Paradigm
- ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries
- Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- Streaming Model Cascades for Semantic SQL
- Abacus: A Cost-Based Optimizer for Semantic Operator Systems
- The Stretto Execution Engine for LLM-Augmented Data Systems
- Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and Analysis
- Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees
Related papers
- Beyond Overlap: Hierarchical Graph Abstraction for Out-of-Core Vector Search
- EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
- Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database
- Samyama: A Unified Graph-Vector Database with In-Database Optimization, Agentic Enrichment, and Hardware Acceleration
- GenTUS: Table Union Search via Constrained Generation of Semantic Table Identifiers
- Common-Neighbor-Count-Based Representative Possible World Finding on Uncertain Graphs