TableCopilot: A Table Assistant Empowered by Natural Language Conditional Table Discovery

2025-07-10

AI Summary

Existing table assistant systems predominantly assume users already possess structured tables, neglecting the challenge of efficiently discovering relevant tables from large-scale table corpora under natural language conditions. This paper introduces “Natural Language Condition–Driven Table Discovery” (NLC-TD), a novel task that establishes an interactive, precise, and personalized table discovery and analysis paradigm. To address this, we propose Crofuma, a cross-modal fusion architecture that jointly models textual queries and tabular structure/content to achieve semantic alignment and fine-grained relevance ranking. Evaluated on standard benchmarks, our approach improves NDCG@5 by over 12% compared to state-of-the-art single-input baselines. We publicly release the source code, benchmark dataset, and educational resources to foster research and practical applications in table intelligence.

Technology Category

• Natural Language Processing: Question Answering
• Data Mining & Knowledge Management: Intelligent Query Processing
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The rise of LLM has enabled natural language-based table assistants, but existing systems assume users already have a well-formed table, neglecting the challenge of table discovery in large-scale table pools. To address this, we introduce TableCopilot, an LLM-powered assistant for interactive, precise, and personalized table discovery and analysis. We define a novel scenario, nlcTD, where users provide both a natural language condition and a query table, enabling intuitive and flexible table discovery for users of all expertise levels. To handle this, we propose Crofuma, a cross-fusion-based approach that learns and aggregates single-modal and cross-modal matching scores. Experimental results show Crofuma outperforms SOTA single-input methods by at least 12% on NDCG@5. We also release an instructional video, codebase, datasets, and other resources on GitHub to encourage community contributions. TableCopilot sets a new standard for interactive table assistants, making advanced table discovery accessible and integrated.

Problem

• Enables natural language-based table discovery in large-scale pools
• Addresses challenge of interactive, precise, personalized table analysis
• Proposes cross-fusion approach for improved table matching performance

Innovation

• LLM-powered assistant for interactive table discovery
• Cross-fusion-based approach for multi-modal matching
• Natural language condition with query table integration