Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

OmniTQA: A Cost-Aware System for Hybrid Query Processing over Semi-Structured Data

Nima Shahbazi, Seiji Maekawa, Nikita Bhutani, Estevam Hruschka

Abstract

While recent advances in large language models have significantly improved Text-to-SQL and table question answering systems, most existing approaches assume that all query-relevant information is explicitly represented in structured schemas. In practice, many enterprise databases contain hybrid schemas where structured attributes coexist with free-form textual fields, requiring systems to reason over both types of information. To address this challenge, we introduce OmniTQA, a cost-aware hybrid query processing framework that operates over both structured and semi-structured data. OmniTQA treats semantic reasoning as a first-class query operator, seamlessly integrating LLM-based semantic operations with classical relational operators into an executable directed acyclic graph. To manage the high latency and cost of LLM inference, it extends classical query optimization with data-aware planning, combining atomic query decomposition and operator reordering to minimize semantic workload. The framework also features a dual-engine execution architecture that dynamically routes tasks between a relational database and an LLM module, using operator-aware batching to scale efficiently. Extensive experiments across a diverse suite of structured and semi-structured table question answering benchmarks demonstrate that OmniTQA consistently outperforms existing symbolic, semantic, and hybrid baselines in both accuracy and cost efficiency. These gains are particularly pronounced for complex queries, large tables and multi-relation schemas.

OmniTQA: A Cost-Aware System for Hybrid Query Processing over Semi-Structured Data

Abstract

While recent advances in large language models have significantly improved Text-to-SQL and table question answering systems, most existing approaches assume that all query-relevant information is explicitly represented in structured schemas. In practice, many enterprise databases contain hybrid schemas where structured attributes coexist with free-form textual fields, requiring systems to reason over both types of information. To address this challenge, we introduce OmniTQA, a cost-aware hybrid query processing framework that operates over both structured and semi-structured data. OmniTQA treats semantic reasoning as a first-class query operator, seamlessly integrating LLM-based semantic operations with classical relational operators into an executable directed acyclic graph. To manage the high latency and cost of LLM inference, it extends classical query optimization with data-aware planning, combining atomic query decomposition and operator reordering to minimize semantic workload. The framework also features a dual-engine execution architecture that dynamically routes tasks between a relational database and an LLM module, using operator-aware batching to scale efficiently. Extensive experiments across a diverse suite of structured and semi-structured table question answering benchmarks demonstrate that OmniTQA consistently outperforms existing symbolic, semantic, and hybrid baselines in both accuracy and cost efficiency. These gains are particularly pronounced for complex queries, large tables and multi-relation schemas.

Paper Structure

This paper contains 38 sections, 6 equations, 14 figures, 8 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. Data Model
  4. Table Question Answering
  5. Problem Formulation
  6. System Overview
  7. Preprocessing
  8. Query-agnostic Preprocessing
  9. Query-aware Preprocessing
  10. Planning
  11. Schema Grounding
  12. Atomic Step Decomposition
  13. Hybrid Operator Model
  14. Plan Optimization
  15. Plan Diversification
  16. ...and 23 more sections

Figures (14)

  • Figure 1: Two instances of NCAA Soccer database with distinct schema representations: (left) structured; (right) semi-structured.
  • Figure 2: End-to-end overview of the OmniTQA framework.
  • Figure 3: Illustration of the OmniTQA planning phase for the UEFA Soccer database and the query "Did the player who achieved the UEFA Men's Player of the Year 2021 win the UCL championship?". OmniTQA first constructs a query-aware data preview $\hat{R}^\mathcal{Q}$ (shown in blue) to ground natural-language intents to schema attributes. The planner then generates and optimizes multiple candidate logical plans to resolve the schema ambiguity over which column encodes the UEFA Men's Player of the Year information. For example, Plan A assumes the information is stored in column "Remark", whereas Plan B assumes it is stored in column "Description", yielding different execution outputs.
  • Figure 4: Accuracy comparison of OmniTQA vs. baselines evaluated with Gemini-3-Flash.
  • Figure 5: Accuracy comparison: GPT-5-Mini.
  • ...and 9 more figures

Theorems & Definitions (2)

  • Definition 1: Table Question Answering ---TQA
  • Definition 2: Semi-structured Table Question Answering --- $\textsf{SSTQA}\xspace$