@inproceedings{miani-etal-2026-pos,
title = "{POS} Tagging with Generative {LLM}s for Historical {G}ermanic Low-Resource Languages: An Evaluation Against Fine-Tuned {BERT}",
author = "Miani, Irene and
Darwin, Gregory and
Stymne, Sara",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages ({LT}4{HALA} 2026) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.lt4hala-1.12/",
doi = "10.63317/2r9n7btigbd6",
pages = "125--138",
abstract = "Part-of-Speech (POS) tagging is a fundamental task in Natural Language Processing, yet its performance on historical low-resource languages is still underexplored, particularly in the context of large generative models. While recent studies have demonstrated strong results for Large Language Models (LLMs) on modern languages and contemporary low-resource settings, their effectiveness for historical varieties remains unclear. Moreover, genre-specific structural variation, which may substantially affect tagging performance, has received limited attention. This study evaluates the zero- and few-shot POS tagging performance of two generative models on four historical Germanic low-resource languages across two literary genres. Their performance is benchmarked against fine-tuned BERT models. To contextualize the performance on historical data, the models are also evaluated on two modern languages. The results show that fine-tuned encoder models consistently outperform generative models across all settings. The performance of the LLMs on historical languages is substantially lower compared to that on modern languages, suggesting limited representation of these varieties in pretraining data. Furthermore, error analysis reveals structural output inconsistencies in LLM predictions that require additional post-processing. These findings highlight the limitations of zero- and few-shot generative models for historical low-resource POS tagging and underline the importance of task-specific fine-tuning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miani-etal-2026-pos">
<titleInfo>
<title>POS Tagging with Generative LLMs for Historical Germanic Low-Resource Languages: An Evaluation Against Fine-Tuned BERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Irene</namePart>
<namePart type="family">Miani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gregory</namePart>
<namePart type="family">Darwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Stymne</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 Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</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>Part-of-Speech (POS) tagging is a fundamental task in Natural Language Processing, yet its performance on historical low-resource languages is still underexplored, particularly in the context of large generative models. While recent studies have demonstrated strong results for Large Language Models (LLMs) on modern languages and contemporary low-resource settings, their effectiveness for historical varieties remains unclear. Moreover, genre-specific structural variation, which may substantially affect tagging performance, has received limited attention. This study evaluates the zero- and few-shot POS tagging performance of two generative models on four historical Germanic low-resource languages across two literary genres. Their performance is benchmarked against fine-tuned BERT models. To contextualize the performance on historical data, the models are also evaluated on two modern languages. The results show that fine-tuned encoder models consistently outperform generative models across all settings. The performance of the LLMs on historical languages is substantially lower compared to that on modern languages, suggesting limited representation of these varieties in pretraining data. Furthermore, error analysis reveals structural output inconsistencies in LLM predictions that require additional post-processing. These findings highlight the limitations of zero- and few-shot generative models for historical low-resource POS tagging and underline the importance of task-specific fine-tuning.</abstract>
<identifier type="citekey">miani-etal-2026-pos</identifier>
<identifier type="doi">10.63317/2r9n7btigbd6</identifier>
<location>
<url>https://aclanthology.org/2026.lt4hala-1.12/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>125</start>
<end>138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T POS Tagging with Generative LLMs for Historical Germanic Low-Resource Languages: An Evaluation Against Fine-Tuned BERT
%A Miani, Irene
%A Darwin, Gregory
%A Stymne, Sara
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F miani-etal-2026-pos
%X Part-of-Speech (POS) tagging is a fundamental task in Natural Language Processing, yet its performance on historical low-resource languages is still underexplored, particularly in the context of large generative models. While recent studies have demonstrated strong results for Large Language Models (LLMs) on modern languages and contemporary low-resource settings, their effectiveness for historical varieties remains unclear. Moreover, genre-specific structural variation, which may substantially affect tagging performance, has received limited attention. This study evaluates the zero- and few-shot POS tagging performance of two generative models on four historical Germanic low-resource languages across two literary genres. Their performance is benchmarked against fine-tuned BERT models. To contextualize the performance on historical data, the models are also evaluated on two modern languages. The results show that fine-tuned encoder models consistently outperform generative models across all settings. The performance of the LLMs on historical languages is substantially lower compared to that on modern languages, suggesting limited representation of these varieties in pretraining data. Furthermore, error analysis reveals structural output inconsistencies in LLM predictions that require additional post-processing. These findings highlight the limitations of zero- and few-shot generative models for historical low-resource POS tagging and underline the importance of task-specific fine-tuning.
%R 10.63317/2r9n7btigbd6
%U https://aclanthology.org/2026.lt4hala-1.12/
%U https://doi.org/10.63317/2r9n7btigbd6
%P 125-138
Markdown (Informal)
[POS Tagging with Generative LLMs for Historical Germanic Low-Resource Languages: An Evaluation Against Fine-Tuned BERT](https://aclanthology.org/2026.lt4hala-1.12/) (Miani et al., LT4HALA 2026)
ACL