# KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts

## TL;DR

KRETA is a comprehensive benchmark designed to evaluate Korean VQA models' ability to understand and reason over text in diverse visual contexts, addressing a significant gap in low-resource language evaluation.

## Contribution

We introduce KRETA, a novel Korean Text-Rich VQA benchmark with a semi-automated data generation pipeline and a rigorous evaluation protocol, enabling detailed assessment of visual text understanding and reasoning.

## Key findings

- KRETA covers 15 domains and 26 image types for thorough evaluation.
- The benchmark includes a semi-automated, high-quality data generation pipeline.
- KRETA's evaluation protocol ensures reliable assessment of model capabilities.

## Abstract

Understanding and reasoning over text within visual contexts poses a significant challenge for Vision-Language Models (VLMs), given the complexity and diversity of real-world scenarios. To address this challenge, text-rich Visual Question Answering (VQA) datasets and benchmarks have emerged for high-resource languages like English. However, a critical gap persists for low-resource languages such as Korean, where the lack of comprehensive benchmarks hinders robust model evaluation and comparison. To bridge this gap, we introduce KRETA, a benchmark for Korean Reading and rEasoning in Text-rich VQA Attuned to diverse visual contexts. KRETA facilitates an in-depth evaluation of both visual text understanding and reasoning capabilities, while also supporting a multifaceted assessment across 15 domains and 26 image types. Additionally, we introduce a semi-automated VQA generation pipeline specifically optimized for text-rich settings, leveraging refined stepwise image decomposition and a rigorous seven-metric evaluation protocol to ensure data quality. While KRETA is tailored for Korean, we hope our adaptable and extensible pipeline will facilitate the development of similar benchmarks in other languages, thereby accelerating multilingual VLM research. The code and dataset for KRETA are available at https://github.com/tabtoyou/KRETA.