LLM post-correction substantially lowers character match error on historical OCR, but gains vary by language and noise and over-correction remains a risk on clean inputs.
In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents
LLM post-correction substantially lowers character match error on historical OCR, but gains vary by language and noise and over-correction remains a risk on clean inputs.