@inproceedings{oai:ipsj.ixsq.nii.ac.jp:00241512,
 author = {Clanuwat, Tarin and Zhao Tianyu and Imajuku, Yuki and Kitamoto, Asanobu and Tarin, Clanuwat and Tianyu Zhao and Yuki Imajuku and Asanobu Kitamoto},
 book = {じんもんこん2024論文集},
 month = {Nov},
 note = {This paper presents a methodology for enhancing Optical Character Recognition (OCR) accuracy for historical Japanese documents, using Large Language Models (LLMs). We experimented with six open-source LLMs, ranging in size from 7 to 14 billion parameters, developing two models—a next-token prediction model and an OCR text refiner—both fine-tuned on classical Japanese text from the Minna de Honkoku project. Our approach significantly reduces the Character Error Rate (CER) by correcting misidentified characters and reordering incorrect sequences, particularly improving the recognition of Katakana and Kanji characters often misinterpreted by RURI Kuzushiji OCR model. The findings demonstrate the potential of advanced LLMs to improve the digitization and preservation of Japanese historical documents., This paper presents a methodology for enhancing Optical Character Recognition (OCR) accuracy for historical Japanese documents, using Large Language Models (LLMs). We experimented with six open-source LLMs, ranging in size from 7 to 14 billion parameters, developing two models—a next-token prediction model and an OCR text refiner—both fine-tuned on classical Japanese text from the Minna de Honkoku project. Our approach significantly reduces the Character Error Rate (CER) by correcting misidentified characters and reordering incorrect sequences, particularly improving the recognition of Katakana and Kanji characters often misinterpreted by RURI Kuzushiji OCR model. The findings demonstrate the potential of advanced LLMs to improve the digitization and preservation of Japanese historical documents.},
 pages = {75--82},
 publisher = {情報処理学会},
 title = {Beyond OCR: Enhancing Classical Japanese Transcription with Large Language Models},
 volume = {2024},
 year = {2024}
}