When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910184766439424 |
|---|---|
| author | Sun, Lin Dexian, Wang Huang, Jingang Zhang, Linglin Jia, Change Cheng, Zhengwei Zhang, Xiangzheng |
| author_facet | Sun, Lin Dexian, Wang Huang, Jingang Zhang, Linglin Jia, Change Cheng, Zhengwei Zhang, Xiangzheng |
| contents | Industrial Retrieval-Augmented Generation (RAG) systems depend on optical character recognition (OCR) to transform visual documents into text. Existing OCR benchmarks rely on character-level metrics, which inadequately measure downstream RAG effectiveness under real-world conditions. We introduce an OCR benchmark for industrial RAG systems covering 11 challenging document types, including extreme layouts, high-resolution pages, complex or watermarked backgrounds, historical documents with non-standard reading orders, visually decorated text, and documents containing tables and mathematical formulas. Evaluating recent SOTA OCR models under a controlled OCR-first RAG pipeline shows clear performance degradation on realistic industrial documents despite strong conventional benchmark scores. We find that high OCR accuracy does not necessarily translate into strong downstream RAG performance: structural and semantic errors can cause substantial retrieval failures even when WER/CER remains low. Further analysis shows that this mismatch is category-dependent, arises through both retrieval-side and downstream generation-side failures, and remains stable across representative OCR-first pipeline choices. The benchmark is publicly available at https://github.com/Qihoo360/InduOCRBench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_00911 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation Sun, Lin Dexian, Wang Huang, Jingang Zhang, Linglin Jia, Change Cheng, Zhengwei Zhang, Xiangzheng Computer Vision and Pattern Recognition Industrial Retrieval-Augmented Generation (RAG) systems depend on optical character recognition (OCR) to transform visual documents into text. Existing OCR benchmarks rely on character-level metrics, which inadequately measure downstream RAG effectiveness under real-world conditions. We introduce an OCR benchmark for industrial RAG systems covering 11 challenging document types, including extreme layouts, high-resolution pages, complex or watermarked backgrounds, historical documents with non-standard reading orders, visually decorated text, and documents containing tables and mathematical formulas. Evaluating recent SOTA OCR models under a controlled OCR-first RAG pipeline shows clear performance degradation on realistic industrial documents despite strong conventional benchmark scores. We find that high OCR accuracy does not necessarily translate into strong downstream RAG performance: structural and semantic errors can cause substantial retrieval failures even when WER/CER remains low. Further analysis shows that this mismatch is category-dependent, arises through both retrieval-side and downstream generation-side failures, and remains stable across representative OCR-first pipeline choices. The benchmark is publicly available at https://github.com/Qihoo360/InduOCRBench. |
| title | When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.00911 |