Weaver: Interweaving SQL and LLM for Table Reasoning

TL;DR

Weaver is a modular system that dynamically combines SQL and LLMs to improve table question answering, especially for complex queries involving unstructured data, by decomposing tasks into manageable steps.

Contribution

Weaver introduces a flexible, step-by-step pipeline that integrates SQL and LLMs for enhanced accuracy and adaptability in table-based question answering.

Findings

Outperforms state-of-the-art methods on four TableQA datasets

Reduces API calls and error rates significantly

Demonstrates improved handling of complex, multi-step queries

Abstract

Querying tables with unstructured data is challenging due to the presence of text (or image), either embedded in the table or in external paragraphs, which traditional SQL struggles to process, especially for tasks requiring semantic reasoning. While Large Language Models (LLMs) excel at understanding context, they face limitations with long input sequences. Existing approaches that combine SQL and LLMs typically rely on rigid, predefined work-flows, limiting their adaptability to complex queries. To address these issues, we introduce Weaver , a modular pipeline that dynamically integrates SQL and LLMs for table-based question answering (TableQA). Weaver generates a flexible, step-by-step plan that combines SQL for structured data retrieval with LLMs for semantic processing. By decomposing complex queries into manageable subtasks, Weaver improves accuracy and generalization. Our experiments show that Weaver consistently outperforms state-of-the-art methods across four TableQA datasets, reducing both API calls and error rates. The code, along with other associated scripts, are available at https://coral-lab-asu.github.io/weaver.