@inproceedings{bacciu-etal-2024-dantellm-lets,
title = "{D}ante{LLM}: Let{'}s Push {I}talian {LLM} Research Forward!",
author = "Bacciu, Andrea and
Campagnano, Cesare and
Trappolini, Giovanni and
Silvestri, Fabrizio",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.388",
pages = "4343--4355",
abstract = "In recent years, the dominance of Large Language Models (LLMs) in the English language has become evident. However, there remains a pronounced gap in resources and evaluation tools tailored for non-English languages, underscoring a significant disparity in the global AI landscape. This paper seeks to bridge this gap, specifically focusing on the Italian linguistic context. We introduce a novel benchmark, and an open LLM Leaderboard, designed to evaluate LLMs{'} performance in Italian, providing a rigorous framework for comparative analysis. In our assessment of currently available models, we highlight their respective strengths and limitations against this standard. Crucially, we propose {``}DanteLLM{''}, a state-of-the-art LLM dedicated to Italian. Our empirical evaluations underscore Dante{'}s superiority, as it emerges as the most performant model on our benchmark, with improvements by up to 6 points. This research not only marks a significant stride in Italian-centric natural language processing but also offers a blueprint for the development and evaluation of LLMs in other languages, championing a more inclusive AI paradigm. Our code at: https://github.com/RSTLess-research/DanteLLM",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bacciu-etal-2024-dantellm-lets">
<titleInfo>
<title>DanteLLM: Let’s Push Italian LLM Research Forward!</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Bacciu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cesare</namePart>
<namePart type="family">Campagnano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Trappolini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabrizio</namePart>
<namePart type="family">Silvestri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, the dominance of Large Language Models (LLMs) in the English language has become evident. However, there remains a pronounced gap in resources and evaluation tools tailored for non-English languages, underscoring a significant disparity in the global AI landscape. This paper seeks to bridge this gap, specifically focusing on the Italian linguistic context. We introduce a novel benchmark, and an open LLM Leaderboard, designed to evaluate LLMs’ performance in Italian, providing a rigorous framework for comparative analysis. In our assessment of currently available models, we highlight their respective strengths and limitations against this standard. Crucially, we propose “DanteLLM”, a state-of-the-art LLM dedicated to Italian. Our empirical evaluations underscore Dante’s superiority, as it emerges as the most performant model on our benchmark, with improvements by up to 6 points. This research not only marks a significant stride in Italian-centric natural language processing but also offers a blueprint for the development and evaluation of LLMs in other languages, championing a more inclusive AI paradigm. Our code at: https://github.com/RSTLess-research/DanteLLM</abstract>
<identifier type="citekey">bacciu-etal-2024-dantellm-lets</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.388</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4343</start>
<end>4355</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DanteLLM: Let’s Push Italian LLM Research Forward!
%A Bacciu, Andrea
%A Campagnano, Cesare
%A Trappolini, Giovanni
%A Silvestri, Fabrizio
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F bacciu-etal-2024-dantellm-lets
%X In recent years, the dominance of Large Language Models (LLMs) in the English language has become evident. However, there remains a pronounced gap in resources and evaluation tools tailored for non-English languages, underscoring a significant disparity in the global AI landscape. This paper seeks to bridge this gap, specifically focusing on the Italian linguistic context. We introduce a novel benchmark, and an open LLM Leaderboard, designed to evaluate LLMs’ performance in Italian, providing a rigorous framework for comparative analysis. In our assessment of currently available models, we highlight their respective strengths and limitations against this standard. Crucially, we propose “DanteLLM”, a state-of-the-art LLM dedicated to Italian. Our empirical evaluations underscore Dante’s superiority, as it emerges as the most performant model on our benchmark, with improvements by up to 6 points. This research not only marks a significant stride in Italian-centric natural language processing but also offers a blueprint for the development and evaluation of LLMs in other languages, championing a more inclusive AI paradigm. Our code at: https://github.com/RSTLess-research/DanteLLM
%U https://aclanthology.org/2024.lrec-main.388
%P 4343-4355
Markdown (Informal)
[DanteLLM: Let’s Push Italian LLM Research Forward!](https://aclanthology.org/2024.lrec-main.388) (Bacciu et al., LREC-COLING 2024)
ACL
- Andrea Bacciu, Cesare Campagnano, Giovanni Trappolini, and Fabrizio Silvestri. 2024. DanteLLM: Let’s Push Italian LLM Research Forward!. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4343–4355, Torino, Italia. ELRA and ICCL.