@inproceedings{chatzikyriakidis-etal-2026-perplexity,
title = "Perplexity as a Metric for Dialectal Distance: A Computational Study of {G}reek Varieties",
author = "Chatzikyriakidis, Stergios and
Psaltaki, Erofili and
Papadakis, Dimitrios and
Henriksson, Erik and
Laippala, Veronika",
booktitle = "Proceedings of the 13th Workshop on {NLP} for Similar Languages, Varieties and Dialects",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.vardial-1.8/",
pages = "101--112",
abstract = "In this paper, we use LLM perplexity as a measure to assess Greek dialectal distance. We test seven models on Standard Modern Greek (SMG) and eight dialects, namely Heptanesian, Cypriot, Maniot, Pontic, Northern, Cretan, Tsakonian, and Griko. Using samples of 5k, 15k, and 25k tokens from the GRDD+ corpus for each variety, we find a consistent dialect ranking across models, with Heptanesian closest to SMG, and Griko most distant (perplexity ratio 3.6{--}14.5{\texttimes} depending on model). These results are largely in agreement with theoretical dialectological knowledge. For example, Tsakonian consistently appears distant in all measures, reflecting its status as the sole Doric descendant, while Heptanesian appears closer by all metrics, pointing to its status as one of the dialects used to shape the official variety. Perplexity correlates strongly with Bits Per-Character (mean r = 0.94) and Normalized Compression Distance (mean r = 0.87, range 0.76{--}0.93), providing support for its use as a dialectometric tool. However, a number of important confounds are also found. First, tokenization effects compress Llama 2{'}s perplexity range. Second, genre artifacts seem to inflate the results for Cretan. Third, potential training data contamination likely reduces perplexity for Cypriot and Pontic. Lastly, we find that Greek-specific models like Meltemi and Krikri do not consistently outperform general models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chatzikyriakidis-etal-2026-perplexity">
<titleInfo>
<title>Perplexity as a Metric for Dialectal Distance: A Computational Study of Greek Varieties</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stergios</namePart>
<namePart type="family">Chatzikyriakidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erofili</namePart>
<namePart type="family">Psaltaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitrios</namePart>
<namePart type="family">Papadakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Henriksson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Laippala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we use LLM perplexity as a measure to assess Greek dialectal distance. We test seven models on Standard Modern Greek (SMG) and eight dialects, namely Heptanesian, Cypriot, Maniot, Pontic, Northern, Cretan, Tsakonian, and Griko. Using samples of 5k, 15k, and 25k tokens from the GRDD+ corpus for each variety, we find a consistent dialect ranking across models, with Heptanesian closest to SMG, and Griko most distant (perplexity ratio 3.6–14.5× depending on model). These results are largely in agreement with theoretical dialectological knowledge. For example, Tsakonian consistently appears distant in all measures, reflecting its status as the sole Doric descendant, while Heptanesian appears closer by all metrics, pointing to its status as one of the dialects used to shape the official variety. Perplexity correlates strongly with Bits Per-Character (mean r = 0.94) and Normalized Compression Distance (mean r = 0.87, range 0.76–0.93), providing support for its use as a dialectometric tool. However, a number of important confounds are also found. First, tokenization effects compress Llama 2’s perplexity range. Second, genre artifacts seem to inflate the results for Cretan. Third, potential training data contamination likely reduces perplexity for Cypriot and Pontic. Lastly, we find that Greek-specific models like Meltemi and Krikri do not consistently outperform general models.</abstract>
<identifier type="citekey">chatzikyriakidis-etal-2026-perplexity</identifier>
<location>
<url>https://aclanthology.org/2026.vardial-1.8/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>101</start>
<end>112</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Perplexity as a Metric for Dialectal Distance: A Computational Study of Greek Varieties
%A Chatzikyriakidis, Stergios
%A Psaltaki, Erofili
%A Papadakis, Dimitrios
%A Henriksson, Erik
%A Laippala, Veronika
%S Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F chatzikyriakidis-etal-2026-perplexity
%X In this paper, we use LLM perplexity as a measure to assess Greek dialectal distance. We test seven models on Standard Modern Greek (SMG) and eight dialects, namely Heptanesian, Cypriot, Maniot, Pontic, Northern, Cretan, Tsakonian, and Griko. Using samples of 5k, 15k, and 25k tokens from the GRDD+ corpus for each variety, we find a consistent dialect ranking across models, with Heptanesian closest to SMG, and Griko most distant (perplexity ratio 3.6–14.5× depending on model). These results are largely in agreement with theoretical dialectological knowledge. For example, Tsakonian consistently appears distant in all measures, reflecting its status as the sole Doric descendant, while Heptanesian appears closer by all metrics, pointing to its status as one of the dialects used to shape the official variety. Perplexity correlates strongly with Bits Per-Character (mean r = 0.94) and Normalized Compression Distance (mean r = 0.87, range 0.76–0.93), providing support for its use as a dialectometric tool. However, a number of important confounds are also found. First, tokenization effects compress Llama 2’s perplexity range. Second, genre artifacts seem to inflate the results for Cretan. Third, potential training data contamination likely reduces perplexity for Cypriot and Pontic. Lastly, we find that Greek-specific models like Meltemi and Krikri do not consistently outperform general models.
%U https://aclanthology.org/2026.vardial-1.8/
%P 101-112
Markdown (Informal)
[Perplexity as a Metric for Dialectal Distance: A Computational Study of Greek Varieties](https://aclanthology.org/2026.vardial-1.8/) (Chatzikyriakidis et al., VarDial 2026)
ACL