OCR Error Post-Correction with LLMs in Historical Documents: No Free Lunches
This addresses the problem of improving text quality in historical corpora for researchers and archivists, but it is incremental as it evaluates existing methods on new data.
The study tackled OCR error correction in historical documents using open-weight LLMs, finding that while they reduced character error rates in English, performance for Finnish was not practically useful.
Optical Character Recognition (OCR) systems often introduce errors when transcribing historical documents, leaving room for post-correction to improve text quality.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.