LLM-Driven Online Aggregation for Unstructured Text Analytics

2026-03-09

AI Summary

This work addresses the high latency of large language models (LLMs) in text analysis, which often impedes real-time applications. To overcome this limitation, the authors propose OLLA, a novel framework that integrates semantic stratified sampling, incremental structured transformation, and online aggregation to embed LLMs within relational query processing. This design enables progressive semantic analysis and rapid convergence to accurate results. Experimental evaluation across multiple domains demonstrates that OLLA achieves sub-1% error accuracy while requiring less than 4% of the full processing time, yielding speedups ranging from 1.6× to 38× compared to conventional approaches.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Data Mining & Knowledge Management: Intelligent Query Processing

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Large Language Models (LLMs) exhibit strong capabilities in text processing, and recent research has augmented SQL and DataFrame with LLM-powered semantic operators for data analysis. However, LLM-based data processing is hindered by slower token generation speeds compared to relational queries. To enhance real-time responsiveness, we propose OLLA, an LLM-driven online aggregation framework that accelerates semantic processing within relational queries. In contrast to batch-processing systems that yield results only after the entire dataset is processed, our approach incrementally transforms text into a structured data stream and applies online aggregation to provide progressive output. To enhance our online aggregation process, we introduce a semantic stratified sampling approach that improves data selection and expedites convergence to the ground truth. Evaluations show that OLLA reaches 1% accuracy error bound compared with labeled ground truth using less than 4% of the full-data time. It achieves speedups ranging from 1.6$\times$ to 38$\times$ across diverse domains, measured by comparing the time to reach a 5% error bound with that of full-data time. We release our code at https://github.com/olla-project/llm-online-agg.git.

Problem

• LLM
• online aggregation
• unstructured text analytics
• real-time responsiveness
• semantic processing

Innovation

• LLM-driven online aggregation
• semantic stratified sampling
• incremental text processing
• progressive query response
• unstructured text analytics