publications

2025

1. ACL ARR

   REaR: Retrieve, Expand and Refine for Effective Multitable Retrieval

   Himanshu Singhal, Rishita Agarwal, Peter Baile Chen, and 3 more authors

   ACL ARR 2025 October Submission, 2025

   Abs Bib

   Answering natural language queries over relational data often requires retrieving and reasoning over multiple tables, yet most retrievers optimize only for query-table relevance and ignore table–table compatibility. We introduce REaR (Retrieve, Expand and Refine), a three-stage, LLM-free framework that separates semantic relevance from structural joinability for efficient, high-fidelity multi-table retrieval. REaR (i) retrieves query-aligned tables, (ii) expands these with structurally joinable tables via fast, precomputed column-embedding comparisons, and (iii) refines them by pruning noisy or weakly related candidates. Empirically, REaR is retriever-agnostic and consistently improves dense/sparse retrievers on complex table QA datasets (BIRD, MMQA, and Spider) by improving both multi-table retrieval quality and downstream SQL execution. Despite being LLM-free, it delivers performance competitive with state-of-the-art LLM-augmented retrieval systems (e.g., ARM) while achieving much lower latency and cost. Ablations confirm complementary gains from expansion and refinement, underscoring REaR as a practical, scalable building block for table-based downstream tasks (e.g., Text-to-SQL).

   @article{agarwal2025rear,
     title = {{REaR: Retrieve, Expand and Refine for Effective Multitable Retrieval}},
     author = {Singhal, Himanshu and Agarwal, Rishita and Chen, Peter Baile and Choudhury, Manan Roy and Roth, Dan and Gupta, Vivek},
     journal = {ACL ARR 2025 October Submission},
     year = {2025},
   }