Year: 2025
Type: conference-paper
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 LLM typically rely on rigid, predefined workflows, limiting their adaptability to complex queries.To address these issues, we introduce Weaver , a modular pipeline that dynamically integrates SQL and LLM for table-based question answering (Table QA).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-ofthe-art methods across four Table QA datasets, reducing both API calls and error rates.
Authors: Rohit Khoja, Devanshu Gupta, Yanjie Fu, Dan Roth, Vivek Gupta
Institutions: Arizona State University, University of Pennsylvania
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: Collaborative Research: III: Small: Closing Sim-to-Real Gap in Reinforcement Learning via Randomization, Alignment, and Derivation, Collaborative Research: III: Small: Advancing Data-Centric AI through Generative Approaches for Feature Space Reconstruction, III: Small: Deep Interactive Reinforcement Learning for Self-optimizing Feature Selection, CAREER: Reinforced Imitative Graph Learning: Bridging the Gap between Perception and Prescription in Graph Sequences, Collaborative Research: SHF: Small: Decentralized Edge Computing Platform for Privacy-Preserving Mobile Crowdsensing, G8876996369
OpenAlex ID: W4416035615