@inproceedings{thomas-etal-2026-image,
title = "Image-Informed Post-{OCR} Correction with Vision-Language Models",
author = "Thomas, Alan and
Liu, Xianyuan and
Lu, Haiping and
Gaizauskas, Robert J.",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.60/",
pages = "1224--1237",
ISBN = "979-8-89176-462-0",
abstract = "Improving the quality of OCR transcriptions is crucial for researchers working with digital archives, as OCR errors hinder readability and downstream NLP tasks. While prior work has focused on seq2seq neural machine translation and, more recently, prompt-based approaches with large language models (LLMs), these methods rely solely on text, overlooking the visual characteristics of source documents. In this work, we explore the potential of vision-language models (VLMs) for post-OCR correction to evaluate the impact of integrating visual information. We conduct experiments on the BLN600 dataset of 19th-century newspaper articles, comparing Llama 3.2 Vision and Qwen 2.5 VL to their text-only LLM counterparts. Our results show that VLMs significantly outperform LLMs, achieving approximately 90{\%} reduction in character and word error rates, with the optimal setting being one that takes as input both document image and prior noisy OCR. This suggests that VLM-based post-OCR correction can be a viable and effective approach for correcting back catalogues of poorly OCR{'}ed historical documents and improving the usability of digital archives."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thomas-etal-2026-image">
<titleInfo>
<title>Image-Informed Post-OCR Correction with Vision-Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Thomas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiping</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Gaizauskas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Improving the quality of OCR transcriptions is crucial for researchers working with digital archives, as OCR errors hinder readability and downstream NLP tasks. While prior work has focused on seq2seq neural machine translation and, more recently, prompt-based approaches with large language models (LLMs), these methods rely solely on text, overlooking the visual characteristics of source documents. In this work, we explore the potential of vision-language models (VLMs) for post-OCR correction to evaluate the impact of integrating visual information. We conduct experiments on the BLN600 dataset of 19th-century newspaper articles, comparing Llama 3.2 Vision and Qwen 2.5 VL to their text-only LLM counterparts. Our results show that VLMs significantly outperform LLMs, achieving approximately 90% reduction in character and word error rates, with the optimal setting being one that takes as input both document image and prior noisy OCR. This suggests that VLM-based post-OCR correction can be a viable and effective approach for correcting back catalogues of poorly OCR’ed historical documents and improving the usability of digital archives.</abstract>
<identifier type="citekey">thomas-etal-2026-image</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.60/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1224</start>
<end>1237</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Image-Informed Post-OCR Correction with Vision-Language Models
%A Thomas, Alan
%A Liu, Xianyuan
%A Lu, Haiping
%A Gaizauskas, Robert J.
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F thomas-etal-2026-image
%X Improving the quality of OCR transcriptions is crucial for researchers working with digital archives, as OCR errors hinder readability and downstream NLP tasks. While prior work has focused on seq2seq neural machine translation and, more recently, prompt-based approaches with large language models (LLMs), these methods rely solely on text, overlooking the visual characteristics of source documents. In this work, we explore the potential of vision-language models (VLMs) for post-OCR correction to evaluate the impact of integrating visual information. We conduct experiments on the BLN600 dataset of 19th-century newspaper articles, comparing Llama 3.2 Vision and Qwen 2.5 VL to their text-only LLM counterparts. Our results show that VLMs significantly outperform LLMs, achieving approximately 90% reduction in character and word error rates, with the optimal setting being one that takes as input both document image and prior noisy OCR. This suggests that VLM-based post-OCR correction can be a viable and effective approach for correcting back catalogues of poorly OCR’ed historical documents and improving the usability of digital archives.
%U https://aclanthology.org/2026.findings-emnlp.60/
%P 1224-1237
Markdown (Informal)
[Image-Informed Post-OCR Correction with Vision-Language Models](https://aclanthology.org/2026.findings-emnlp.60/) (Thomas et al., Findings 2026)
ACL