AI RESEARCH

FGTR: Fine-Grained Multi-Table Retrieval via Hierarchical LLM Reasoning

arXiv CS.LG

ArXi:2603.12702v1 Announce Type: cross With the rapid advancement of large language models (LLMs), growing efforts have been made on LLM-based table retrieval. However, existing studies typically focus on single-table query, and implement it by similarity matching after encoding the entire table. These methods usually result in low accuracy due to their coarse-grained encoding which incorporates much query-irrelated data, and are also inefficient when dealing with large tables, failing to fully utilize the reasoning capabilities of