@inproceedings{fittschen-etal-2026-pretraining,
title = "Pretraining Language Models for Diachronic Linguistic Change Discovery",
author = "Fittschen, Elisabeth and
Li, Sabrina Xin and
Lippincott, Tom and
Choshen, Leshem and
Messner, Craig",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.241/",
pages = "4627--4642",
ISBN = "979-8-89176-386-9",
abstract = "Large language models (LLMs) are increasingly used as knowledge discovery tools. Humanistic disciplines like historical linguistics and literary studies have shown interest in this capability. These fields often construct arguments on the basis of distinctions between phenomena like time-period or genre. Such methodological investments complicate reliance on LLMs pretrained over large sets of broadly-collected data. We show that efficient pretraining techniques produce useful models of semantic change over modest historical corpora without allowing potential contamination from anachronistic data. We verify that these trained-from-scratch models better respect historical divisions and are more computationally efficient compared to the standard approach of fine-tuning an existing LLM. We compare the trade-offs in general linguistic fluency versus detecting and characterizing various forms of linguistic change, and provide a pipeline implementation of our approach that can be readily adapted and applied to a wide range of diachronic phenomena."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fittschen-etal-2026-pretraining">
<titleInfo>
<title>Pretraining Language Models for Diachronic Linguistic Change Discovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elisabeth</namePart>
<namePart type="family">Fittschen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabrina</namePart>
<namePart type="given">Xin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Lippincott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leshem</namePart>
<namePart type="family">Choshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Craig</namePart>
<namePart type="family">Messner</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>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly used as knowledge discovery tools. Humanistic disciplines like historical linguistics and literary studies have shown interest in this capability. These fields often construct arguments on the basis of distinctions between phenomena like time-period or genre. Such methodological investments complicate reliance on LLMs pretrained over large sets of broadly-collected data. We show that efficient pretraining techniques produce useful models of semantic change over modest historical corpora without allowing potential contamination from anachronistic data. We verify that these trained-from-scratch models better respect historical divisions and are more computationally efficient compared to the standard approach of fine-tuning an existing LLM. We compare the trade-offs in general linguistic fluency versus detecting and characterizing various forms of linguistic change, and provide a pipeline implementation of our approach that can be readily adapted and applied to a wide range of diachronic phenomena.</abstract>
<identifier type="citekey">fittschen-etal-2026-pretraining</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.241/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>4627</start>
<end>4642</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pretraining Language Models for Diachronic Linguistic Change Discovery
%A Fittschen, Elisabeth
%A Li, Sabrina Xin
%A Lippincott, Tom
%A Choshen, Leshem
%A Messner, Craig
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F fittschen-etal-2026-pretraining
%X Large language models (LLMs) are increasingly used as knowledge discovery tools. Humanistic disciplines like historical linguistics and literary studies have shown interest in this capability. These fields often construct arguments on the basis of distinctions between phenomena like time-period or genre. Such methodological investments complicate reliance on LLMs pretrained over large sets of broadly-collected data. We show that efficient pretraining techniques produce useful models of semantic change over modest historical corpora without allowing potential contamination from anachronistic data. We verify that these trained-from-scratch models better respect historical divisions and are more computationally efficient compared to the standard approach of fine-tuning an existing LLM. We compare the trade-offs in general linguistic fluency versus detecting and characterizing various forms of linguistic change, and provide a pipeline implementation of our approach that can be readily adapted and applied to a wide range of diachronic phenomena.
%U https://aclanthology.org/2026.findings-eacl.241/
%P 4627-4642
Markdown (Informal)
[Pretraining Language Models for Diachronic Linguistic Change Discovery](https://aclanthology.org/2026.findings-eacl.241/) (Fittschen et al., Findings 2026)
ACL