The Meaning of Beatus: Disambiguating Latin with Contemporary AI Models

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3ANPGAVBIQ" target="_blank" >RIV/00216208:11320/26:NPGAVBIQ - isvavai.cz</a>

Result on the web

<a href="https://clic2025.unica.it/wp-content/uploads/2025/09/45_main_long.pdf" target="_blank" >https://clic2025.unica.it/wp-content/uploads/2025/09/45_main_long.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

The Meaning of Beatus: Disambiguating Latin with Contemporary AI Models

Original language description

The objective of this work is to assess the performance of Large Language Models (LLMs) on the task of Word Sense Disambiguation (WSD) for Latin.We evaluate state-of-the-art LLMs—including GPT-4o-mini and LLaMA variants—in both zero-shot and fine-tuned settings, using a dataset derived from the SemEval-2020 Latin Lexical Semantic Change task. Our study aims to determine whether instruction tuning and task-specific fine-tuning can significantly improve the models’ ability to disambiguate Latin word senses. Results show that while LLMs demonstrate a non-trivial baseline ability in zero-shot settings, fine-tuning – particularly instruction-based – provides improvements in accuracy and F1 scores. These findings highlight the potential of LLMs when applied to low-resourced historical languages.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

CLiC-it 2025

ISBN

—

ISSN

1613-0073

e-ISSN

—

Number of pages

11

Pages from-to

1-11

Publisher name

—

Place of publication

—

Event location

Cagliari, Italy

Event date

Jan 1, 2026

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—