Work

Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answering

Year: 2026
Type: conference-paper
Abstract: Applying language models (LMs) to tables is challenging due to the mismatch between the two-dimensional structure of tables and the one-dimensional inputs expected by LMs.This mismatch forces linearization, making LMs particularly sensitive to irrelevant cells.Subtable selection mitigates this challenge by isolating question-relevant content prior to answer generation.However, existing approaches either rely on independent row or column selection, failing to capture cross-row and cross-column dependencies, or attempt global reasoning and face challenges similar to holistic table QA under noisy contexts.We propose PieTa (Piece of Table), a divide-and-conquer subtable selection framework that progressively aggregates locally selected evidence without requiring explicit global reasoning.PieTa uses an iterative, window-based multi-resolution process to construct compact subtables that capture global dependencies while limiting LM exposure to irrelevant content.Extensive experiments demonstrate that PieTa consistently outperforms prior subtable-based and holistic table QA approaches.Our code is available at https://github.com/MLV-group/ Piece-of-Table.git.
Authors: Wonjin Lee, Kyumin Kim, Sungjae Lee, Jihun Lee, Kwang In Kim
Institution: LG (South Korea)
Language: English
Open Access status: hybrid
OpenAlex ID: W4405269283
FWCI: 2.656
Cites: 33
Cited by: 3
Related to: 10