arxiv:2510.02543

Exploring OCR-augmented Generation for Bilingual VQA

Published on Oct 2

Authors:

Abstract

OCR-augmented generation using Vision Language Models improves performance in multilingual VQA tasks, particularly with the introduction of a new Korean OCR baseline and benchmark.

AI-generated summary

We investigate OCR-augmented generation with Vision Language Models (VLMs), exploring tasks in Korean and English toward multilingualism. To support research in this domain, we train and release KLOCR, a strong bilingual OCR baseline trained on 100M instances to augment VLMs with OCR ability. To complement existing VQA benchmarks, we curate KOCRBench for Korean VQA, and analyze different prompting methods. Extensive experiments show that OCR-extracted text significantly boosts performance across open source and commercial models. Our work offers new insights into OCR-augmented generation for bilingual VQA. Model, code, and data are available at https://github.com/JHLee0513/KLOCR.