@inproceedings{capone-etal-2024-babies,
title = "{B}a{BIE}s: A Benchmark for the Linguistic Evaluation of {I}talian Baby Language Models",
author = "Capone, Luca and
Suozzi, Alice and
Lebani, Gianluca and
Lenci, Alessandro",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the Tenth Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.20/",
pages = "157--170",
ISBN = "979-12-210-7060-6",
abstract = "The possibility of comparing the linguistic competence of Language Models (LMs) to that of children has gained growing attention lately, raising the need for effective tools for evaluating both the former and the latter. To this purpose, we developed a resource for the linguistic evaluation of BabyLMs, which are LMs trained on datasets that comparable to the linguistic stimulus received by children. This resource adapts four standardized tests for the evaluation of linguistic skills of Italian-speaking children (BVL, TROG-2, TCGB-2 and Peabody). To verify the effectiveness of our benchmark, we administered it to Minerva, a LLM pretrained from scratch on Italian. Our results indicate that Minerva struggles to master certain linguistic aspects, achieving an age-equivalent score of 4 years, and that the type of task administered affects the model{'}s performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="capone-etal-2024-babies">
<titleInfo>
<title>BaBIEs: A Benchmark for the Linguistic Evaluation of Italian Baby Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luca</namePart>
<namePart type="family">Capone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Suozzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gianluca</namePart>
<namePart type="family">Lebani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</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">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>The possibility of comparing the linguistic competence of Language Models (LMs) to that of children has gained growing attention lately, raising the need for effective tools for evaluating both the former and the latter. To this purpose, we developed a resource for the linguistic evaluation of BabyLMs, which are LMs trained on datasets that comparable to the linguistic stimulus received by children. This resource adapts four standardized tests for the evaluation of linguistic skills of Italian-speaking children (BVL, TROG-2, TCGB-2 and Peabody). To verify the effectiveness of our benchmark, we administered it to Minerva, a LLM pretrained from scratch on Italian. Our results indicate that Minerva struggles to master certain linguistic aspects, achieving an age-equivalent score of 4 years, and that the type of task administered affects the model’s performance.</abstract>
<identifier type="citekey">capone-etal-2024-babies</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.20/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>157</start>
<end>170</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BaBIEs: A Benchmark for the Linguistic Evaluation of Italian Baby Language Models
%A Capone, Luca
%A Suozzi, Alice
%A Lebani, Gianluca
%A Lenci, Alessandro
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the Tenth Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F capone-etal-2024-babies
%X The possibility of comparing the linguistic competence of Language Models (LMs) to that of children has gained growing attention lately, raising the need for effective tools for evaluating both the former and the latter. To this purpose, we developed a resource for the linguistic evaluation of BabyLMs, which are LMs trained on datasets that comparable to the linguistic stimulus received by children. This resource adapts four standardized tests for the evaluation of linguistic skills of Italian-speaking children (BVL, TROG-2, TCGB-2 and Peabody). To verify the effectiveness of our benchmark, we administered it to Minerva, a LLM pretrained from scratch on Italian. Our results indicate that Minerva struggles to master certain linguistic aspects, achieving an age-equivalent score of 4 years, and that the type of task administered affects the model’s performance.
%U https://aclanthology.org/2024.clicit-1.20/
%P 157-170
Markdown (Informal)
[BaBIEs: A Benchmark for the Linguistic Evaluation of Italian Baby Language Models](https://aclanthology.org/2024.clicit-1.20/) (Capone et al., CLiC-it 2024)
ACL