Research

Paper

AI LLM March 09, 2026

LLM-Driven Online Aggregation for Unstructured Text Analytics

Authors

Chao Hui, Weizheng Lu, Yanjie Gao, Lingfeng Xiong, Yunhai Wang, Yueguo Chen

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.

Metadata

arXiv ID: 2603.08443
Provider: ARXIV
Primary Category: cs.DB
Published: 2026-03-09
Fetched: 2026-03-10 05:43

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.08443v1</id>\n    <title>LLM-Driven Online Aggregation for Unstructured Text Analytics</title>\n    <updated>2026-03-09T14:40:17Z</updated>\n    <link href='https://arxiv.org/abs/2603.08443v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.08443v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.DB'/>\n    <published>2026-03-09T14:40:17Z</published>\n    <arxiv:comment>DASFAA 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.DB'/>\n    <author>\n      <name>Chao Hui</name>\n    </author>\n    <author>\n      <name>Weizheng Lu</name>\n    </author>\n    <author>\n      <name>Yanjie Gao</name>\n    </author>\n    <author>\n      <name>Lingfeng Xiong</name>\n    </author>\n    <author>\n      <name>Yunhai Wang</name>\n    </author>\n    <author>\n      <name>Yueguo Chen</name>\n    </author>\n  </entry>"
}