RITT: a Retrieval-assisted framework with Image and Text Table representations for table question answering

  • Tables can be represented either as text or as images. Previous works on table question answering (TQA) typically rely on only one representation, neglecting the potential benefits of combining both. In this work, we explore integrating textual and visual table representations using multi-modal large language models (MLLMs) for TQA. Specifically, we propose RITT, a retrieval-assisted framework that first identifies the most relevant part of a table for a given question, then dynamically selects the optimal table representations based on the question type. Experiments demonstrate that our framework significantly outperforms the baseline MLLMs by an average of 13 Exact Match and surpasses two text-only state-of-the-art TQA methods on four TQA benchmarks, highlighting the benefits of leveraging both textual and visual table representations.

Download full text files

Export metadata

Statistics

Number of document requests

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Wei Zhou, Mohsen Mesgar, Heike Adel, Annemarie FriedrichORCiDGND
URN:urn:nbn:de:bvb:384-opus4-1264028
Frontdoor URLhttps://opus.bibliothek.uni-augsburg.de/opus4/126402
ISBN:979-8-89176-268-8OPAC
Parent Title (English):Proceedings of the 4th Table Representation Learning Workshop, 31 July, 2025, Vienna, Austria
Publisher:Association for Computational Linguistics (ACL)
Place of publication:Stroudsburg, PA
Editor:Shuaichen Chang, Madelon Hulsebos, Qian Liu, Wenhu Chen, Huan Sun
Type:Conference Proceeding
Language:English
Date of Publication (online):2025/11/19
Year of first Publication:2025
Publishing Institution:Universität Augsburg
Release Date:2025/11/26
First Page:86
Last Page:97
DOI:https://doi.org/10.18653/v1/2025.trl-1.8
Institutes:Fakultät für Angewandte Informatik
Fakultät für Angewandte Informatik / Institut für Informatik
Fakultät für Angewandte Informatik / Institut für Informatik / Lehrstuhl für Computerlinguistik
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):CC-BY 4.0: Creative Commons: Namensnennung

OPUS4 Logo