GRIT: Guided Relational Integration for Efficient Multi-Table Understanding

Recent advances in large language models (LLMs) have opened new possibilities for tablebased tasks. However, most existing methods remain confined to single-table settings, limiting their applicability to real-world databases composed of multiple interrelated tables. In multi-table scenarios, LLMs face two key challenges: reasoning over relational structures beyond sequential text, and handling the input length limitations imposed by large-scale table concatenation. To address these issues, we propose Guided Relational Integration for multiple Tables (GRIT), a lightweight method that converts relational schemas into LLMfriendly textual representations. GRIT employs hashing-based techniques to efficiently infer primary-foreign key relationships and constructs prompts that explicitly encode relevant join paths and question-relevant columns. GRIT consistently improves table-column retrieval performance across diverse multi-table benchmarks while significantly reducing memory and computational overhead.