OCR Error Post-Correction with LLMs in Historical Documents: No Free Lunches
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917910181576704 |
|---|---|
| author | Kanerva, Jenna Ledins, Cassandra Käpyaho, Siiri Ginter, Filip |
| author_facet | Kanerva, Jenna Ledins, Cassandra Käpyaho, Siiri Ginter, Filip |
| contents | Optical Character Recognition (OCR) systems often introduce errors when transcribing historical documents, leaving room for post-correction to improve text quality. This study evaluates the use of open-weight LLMs for OCR error correction in historical English and Finnish datasets. We explore various strategies, including parameter optimization, quantization, segment length effects, and text continuation methods. Our results demonstrate that while modern LLMs show promise in reducing character error rates (CER) in English, a practically useful performance for Finnish was not reached. Our findings highlight the potential and limitations of LLMs in scaling OCR post-correction for large historical corpora. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_01205 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OCR Error Post-Correction with LLMs in Historical Documents: No Free Lunches Kanerva, Jenna Ledins, Cassandra Käpyaho, Siiri Ginter, Filip Computation and Language Optical Character Recognition (OCR) systems often introduce errors when transcribing historical documents, leaving room for post-correction to improve text quality. This study evaluates the use of open-weight LLMs for OCR error correction in historical English and Finnish datasets. We explore various strategies, including parameter optimization, quantization, segment length effects, and text continuation methods. Our results demonstrate that while modern LLMs show promise in reducing character error rates (CER) in English, a practically useful performance for Finnish was not reached. Our findings highlight the potential and limitations of LLMs in scaling OCR post-correction for large historical corpora. |
| title | OCR Error Post-Correction with LLMs in Historical Documents: No Free Lunches |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.01205 |