Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.02543 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912625462345728 |
|---|---|
| author | Lee, JoonHo Park, Sunho |
| author_facet | Lee, JoonHo Park, Sunho |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02543 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring OCR-augmented Generation for Bilingual VQA Lee, JoonHo Park, Sunho Computer Vision and Pattern Recognition 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. |
| title | Exploring OCR-augmented Generation for Bilingual VQA |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.02543 |