Decomposition-Driven Multi-Table Retrieval and Reasoning for Numerical Question Answering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908873122643968 |
|---|---|
| author | Luo, Feng Lan, Hai Luo, Hui Bao, Zhifeng Wang, Xiaoli Culpepper, J. Shane Sadiq, Shazia |
| author_facet | Luo, Feng Lan, Hai Luo, Hui Bao, Zhifeng Wang, Xiaoli Culpepper, J. Shane Sadiq, Shazia |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07950 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Decomposition-Driven Multi-Table Retrieval and Reasoning for Numerical Question Answering Luo, Feng Lan, Hai Luo, Hui Bao, Zhifeng Wang, Xiaoli Culpepper, J. Shane Sadiq, Shazia Databases 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. |
| title | Decomposition-Driven Multi-Table Retrieval and Reasoning for Numerical Question Answering |
| topic | Databases |
| url | https://arxiv.org/abs/2603.07950 |