ExpliCIT-QA: Explainable Code-Based Image Table Question Answering

doi:10.1007/978-3-032-05179-0_26

ExpliCIT-QA: Explainable Code-Based Image Table Question Answering

2026-01-01

0

PRE

AI

M

Maximiliano Hormazábal Lagos *

Jorge Alcalde Vesteiro

H

Héctor Cerezo‐Costas

DOI：10.1007/978-3-032-05179-0_26

Original

Original request for help

Save

Abstract

En 中文

We present ExpliCIT-QA, a system that extends our previous MRT approach for tabular question answering into a multi-modal pipeline capable of handling complex table images and providing explainable answers. ExpliCIT-QA follows a modular design, consisting of: (1) Multimodal Table Understanding, which uses a Chain-ofThought approach to extract and transform content from table images; (2) Language-based Reasoning, where a step-by-step explanation in natural language is generated to solve the problem; (3) Automatic Code Generation, where Python/Pandas scripts are created based on the reasoning steps, with feedback for handling errors; (4) Code Execution to compute the final answer; and (5) Natural Language Explanation that describes how the answer was computed. The system is built for transparency and auditability: all intermediate outputs, parsed tables, reasoning steps, generated code, and final answers are available for inspection. This strategy works towards closing the explainability gap in end-toend TableVQA systems. We evaluated ExpliCIT-QA on the TableVQABench benchmark, comparing it with existing baselines. We demonstrated improvements in interpretability and transparency, which open the door for applications in sensitive domains like finance and healthcare where auditing results are critical. Code available at https://github.com/maxhormazabal/ExpliCIT.

Keywords:

Visual Question Answering

Tabular Data

Explainability

Chain-of-Thought Reasoning

ExpliCIT-QA: Explainable Code-Based Image Table Question Answering

Abstract

Journal

Organization