@inproceedings{johansson-etal-2026-exploring,
title = "Exploring the similarities and differences between {VLM}-driven and traditional {OCR} for Historical {S}wedish Data",
author = "Johansson, Martin and
Waginder, Selma and
Dann{\'e}lls, Dana",
editor = "Morger, Felix and
Ilinykh, Nikolai and
Scalvini, Barbara and
Dobnik, Simon and
Dann{\'e}lls, Dana",
booktitle = "Proceedings of the Fourth Workshop on the Role of Resources in the Age of Large Language Models ({RESOURCEFUL} 2026)",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.resourceful-4.18/",
doi = "10.63317/4zr3kytoswtq",
pages = "193--199",
abstract = "Recent Swedish OCR efforts rely primarily on traditional OCR methods, including deep CNN{--}LSTM hybrid neural networks and transformer-based models. Some approaches have also demonstrated the applicability of VLM-driven OCR to historical material. However, to date, no studies have examined in depth the performance of VLM-based OCR on historical Swedish sources. In this paper, we ask: How do transformers and VLMs differ in character- and word-level recognition performance across typefaces, and what qualitative differences can be observed in their error patterns? We show that fine-tuned versions of the Alibaba Cloud Qwen3-VL-8B-Instruct and Qwen3-VL-2B-Instruct, combined with a simple repetition-trimming step, outperform conventional OCR systems. Remaining errors are primarily attributable to challenges associated with the Blackletter typeface and formatting issues, such as missing or extra line breaks, characters, and spaces. Even when characters are correctly recognized, formatting inconsistencies can substantially increase transcription error rates."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="johansson-etal-2026-exploring">
<titleInfo>
<title>Exploring the similarities and differences between VLM-driven and traditional OCR for Historical Swedish Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Johansson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Selma</namePart>
<namePart type="family">Waginder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Dannélls</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on the Role of Resources in the Age of Large Language Models (RESOURCEFUL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Morger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Scalvini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Dannélls</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent Swedish OCR efforts rely primarily on traditional OCR methods, including deep CNN–LSTM hybrid neural networks and transformer-based models. Some approaches have also demonstrated the applicability of VLM-driven OCR to historical material. However, to date, no studies have examined in depth the performance of VLM-based OCR on historical Swedish sources. In this paper, we ask: How do transformers and VLMs differ in character- and word-level recognition performance across typefaces, and what qualitative differences can be observed in their error patterns? We show that fine-tuned versions of the Alibaba Cloud Qwen3-VL-8B-Instruct and Qwen3-VL-2B-Instruct, combined with a simple repetition-trimming step, outperform conventional OCR systems. Remaining errors are primarily attributable to challenges associated with the Blackletter typeface and formatting issues, such as missing or extra line breaks, characters, and spaces. Even when characters are correctly recognized, formatting inconsistencies can substantially increase transcription error rates.</abstract>
<identifier type="citekey">johansson-etal-2026-exploring</identifier>
<identifier type="doi">10.63317/4zr3kytoswtq</identifier>
<location>
<url>https://aclanthology.org/2026.resourceful-4.18/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>193</start>
<end>199</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the similarities and differences between VLM-driven and traditional OCR for Historical Swedish Data
%A Johansson, Martin
%A Waginder, Selma
%A Dannélls, Dana
%Y Morger, Felix
%Y Ilinykh, Nikolai
%Y Scalvini, Barbara
%Y Dobnik, Simon
%Y Dannélls, Dana
%S Proceedings of the Fourth Workshop on the Role of Resources in the Age of Large Language Models (RESOURCEFUL 2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F johansson-etal-2026-exploring
%X Recent Swedish OCR efforts rely primarily on traditional OCR methods, including deep CNN–LSTM hybrid neural networks and transformer-based models. Some approaches have also demonstrated the applicability of VLM-driven OCR to historical material. However, to date, no studies have examined in depth the performance of VLM-based OCR on historical Swedish sources. In this paper, we ask: How do transformers and VLMs differ in character- and word-level recognition performance across typefaces, and what qualitative differences can be observed in their error patterns? We show that fine-tuned versions of the Alibaba Cloud Qwen3-VL-8B-Instruct and Qwen3-VL-2B-Instruct, combined with a simple repetition-trimming step, outperform conventional OCR systems. Remaining errors are primarily attributable to challenges associated with the Blackletter typeface and formatting issues, such as missing or extra line breaks, characters, and spaces. Even when characters are correctly recognized, formatting inconsistencies can substantially increase transcription error rates.
%R 10.63317/4zr3kytoswtq
%U https://aclanthology.org/2026.resourceful-4.18/
%U https://doi.org/10.63317/4zr3kytoswtq
%P 193-199
Markdown (Informal)
[Exploring the similarities and differences between VLM-driven and traditional OCR for Historical Swedish Data](https://aclanthology.org/2026.resourceful-4.18/) (Johansson et al., RESOURCEFUL 2026)
ACL