# Decomposition-Driven Multi-Table Retrieval and Reasoning for Numerical Question Answering

Source: [Decomposition-Driven Multi-Table Retrieval and Reasoning for Numerical Question Answering](<https://www.sota2.com/research/paper/69afa5942d603e6de3e43bcb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-11T05:00:11.798Z

Authors: Feng Luo, Hai Lan, Hui Luo, Zhifeng Bao, Xiaoli Wang, J.Shane Culpepper, Shazia Sadiq

Published: 2026-03-09T04:32:20.000Z

## Abstract

In this paper, we study the problem of numerical multi-table question answering (MTQA) over large-scale table collections (e.g., online data repositories). This task is essential in many analytical applications. Existing MTQA solutions, such as text-to-SQL or open-domain MTQA methods, are designed for databases and struggle when applied to large-scale table collections. The key limitations include: (1) Limited support for complex table relationships; (2) Ineffective retrieval of relevant tables at scale; (3) Inaccurate answer generation. To overcome these limitations, we propose DMRAL, a Decomposition-driven Multi-table Retrieval and Answering framework for MTQA over large-scale table collections, which consists of: (1) constructing a table relationship graph to capture complex relationships among tables; (2) Table-Aligned Question Decomposer and Coverage-Aware Retriever, which jointly enable the effective identification of relevant tables from large-scale corpora by enhancing the question decomposition quality and maximizing the question coverage of retrieved tables; and (3) Sub-question Guided Reasoner, which produces correct answers by progressively generating and refining the reasoning program based on sub-questions. Experiments on two MTQA datasets demonstrate that DMRAL significantly outperforms existing state-of-the-art MTQA methods, with an average improvement of 24% in table retrieval and 55% in answer accuracy.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.07950>)

[PDF](<https://arxiv.org/pdf/2603.07950.pdf>)