@inproceedings{onorati-etal-2023-measuring,
title = "Measuring bias in Instruction-Following models with {P}-{AT}",
author = "Onorati, Dario and
Ruzzetti, Elena Sofia and
Venditti, Davide and
Ranaldi, Leonardo and
Zanzotto, Fabio Massimo",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.539/",
doi = "10.18653/v1/2023.findings-emnlp.539",
pages = "8006--8034",
abstract = "Instruction-Following Language Models (IFLMs) are promising and versatile tools for solving many downstream, information-seeking tasks. Given their success, there is an urgent need to have a shared resource to determine whether existing and new IFLMs are prone to produce biased language interactions. In this paper, we propose Prompt Association Test (P-AT): a new resource for testing the presence of social biases in IFLMs. P-AT stems from WEAT (Caliskan et al., 2017) and generalizes the notion of measuring social biases to IFLMs. Basically, we cast WEAT word tests in promptized classification tasks, and we associate a metric - the bias score. Our resource consists of 2310 prompts. We then experimented with several families of IFLMs discovering gender and race biases in all the analyzed models. We expect P-AT to be an important tool for quantifying bias across different dimensions and, therefore, for encouraging the creation of fairer IFLMs before their distortions have consequences in the real world."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="onorati-etal-2023-measuring">
<titleInfo>
<title>Measuring bias in Instruction-Following models with P-AT</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">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">Davide</namePart>
<namePart type="family">Venditti</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>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Instruction-Following Language Models (IFLMs) are promising and versatile tools for solving many downstream, information-seeking tasks. Given their success, there is an urgent need to have a shared resource to determine whether existing and new IFLMs are prone to produce biased language interactions. In this paper, we propose Prompt Association Test (P-AT): a new resource for testing the presence of social biases in IFLMs. P-AT stems from WEAT (Caliskan et al., 2017) and generalizes the notion of measuring social biases to IFLMs. Basically, we cast WEAT word tests in promptized classification tasks, and we associate a metric - the bias score. Our resource consists of 2310 prompts. We then experimented with several families of IFLMs discovering gender and race biases in all the analyzed models. We expect P-AT to be an important tool for quantifying bias across different dimensions and, therefore, for encouraging the creation of fairer IFLMs before their distortions have consequences in the real world.</abstract>
<identifier type="citekey">onorati-etal-2023-measuring</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.539</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.539/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>8006</start>
<end>8034</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring bias in Instruction-Following models with P-AT
%A Onorati, Dario
%A Ruzzetti, Elena Sofia
%A Venditti, Davide
%A Ranaldi, Leonardo
%A Zanzotto, Fabio Massimo
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F onorati-etal-2023-measuring
%X Instruction-Following Language Models (IFLMs) are promising and versatile tools for solving many downstream, information-seeking tasks. Given their success, there is an urgent need to have a shared resource to determine whether existing and new IFLMs are prone to produce biased language interactions. In this paper, we propose Prompt Association Test (P-AT): a new resource for testing the presence of social biases in IFLMs. P-AT stems from WEAT (Caliskan et al., 2017) and generalizes the notion of measuring social biases to IFLMs. Basically, we cast WEAT word tests in promptized classification tasks, and we associate a metric - the bias score. Our resource consists of 2310 prompts. We then experimented with several families of IFLMs discovering gender and race biases in all the analyzed models. We expect P-AT to be an important tool for quantifying bias across different dimensions and, therefore, for encouraging the creation of fairer IFLMs before their distortions have consequences in the real world.
%R 10.18653/v1/2023.findings-emnlp.539
%U https://aclanthology.org/2023.findings-emnlp.539/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.539
%P 8006-8034
Markdown (Informal)
[Measuring bias in Instruction-Following models with P-AT](https://aclanthology.org/2023.findings-emnlp.539/) (Onorati et al., Findings 2023)
ACL
- Dario Onorati, Elena Sofia Ruzzetti, Davide Venditti, Leonardo Ranaldi, and Fabio Massimo Zanzotto. 2023. Measuring bias in Instruction-Following models with P-AT. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8006–8034, Singapore. Association for Computational Linguistics.