@inproceedings{onorati-etal-2024-measuring,
title = "Measuring Bias in Instruction-Following Models with {I}ta{P}-{AT} for the {I}talian Language",
author = "Onorati, Dario and
Venditti, Davide and
Ruzzetti, Elena Sofia and
Ranaldi, Federico and
Ranaldi, Leonardo and
Zanzotto, Fabio Massimo",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th 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-1.76/",
pages = "679--706",
ISBN = "979-12-210-7060-6",
abstract = "Instruction-Following Language Models (IFLMs) are the state-of-the-art for solving many downstream tasks. Given their widespread use, there is an urgent need to measure whether the sentences they generate contain toxic information or social biases. In this paper, we propose Prompt Association Test for the Italian language (ItaP-AT): a new resource for testing the presence of social bias in different domains in IFLMs. This work also aims to understand whether it is possible to make the responses of these models more fair by using context learning, using {\textquotedblleft}one-shot anti-stereotypical prompts{\textquotedblright}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="onorati-etal-2024-measuring">
<titleInfo>
<title>Measuring Bias in Instruction-Following Models with ItaP-AT for the Italian Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dario</namePart>
<namePart type="family">Onorati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Venditti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="given">Sofia</namePart>
<namePart type="family">Ruzzetti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Ranaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Ranaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="given">Massimo</namePart>
<namePart type="family">Zanzotto</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 10th 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>Instruction-Following Language Models (IFLMs) are the state-of-the-art for solving many downstream tasks. Given their widespread use, there is an urgent need to measure whether the sentences they generate contain toxic information or social biases. In this paper, we propose Prompt Association Test for the Italian language (ItaP-AT): a new resource for testing the presence of social bias in different domains in IFLMs. This work also aims to understand whether it is possible to make the responses of these models more fair by using context learning, using “one-shot anti-stereotypical prompts”.</abstract>
<identifier type="citekey">onorati-etal-2024-measuring</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.76/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>679</start>
<end>706</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring Bias in Instruction-Following Models with ItaP-AT for the Italian Language
%A Onorati, Dario
%A Venditti, Davide
%A Ruzzetti, Elena Sofia
%A Ranaldi, Federico
%A Ranaldi, Leonardo
%A Zanzotto, Fabio Massimo
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th 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 onorati-etal-2024-measuring
%X Instruction-Following Language Models (IFLMs) are the state-of-the-art for solving many downstream tasks. Given their widespread use, there is an urgent need to measure whether the sentences they generate contain toxic information or social biases. In this paper, we propose Prompt Association Test for the Italian language (ItaP-AT): a new resource for testing the presence of social bias in different domains in IFLMs. This work also aims to understand whether it is possible to make the responses of these models more fair by using context learning, using “one-shot anti-stereotypical prompts”.
%U https://aclanthology.org/2024.clicit-1.76/
%P 679-706
Markdown (Informal)
[Measuring Bias in Instruction-Following Models with ItaP-AT for the Italian Language](https://aclanthology.org/2024.clicit-1.76/) (Onorati et al., CLiC-it 2024)
ACL