Probing Pre-Trained Language Models for Cross-Cultural Differences in Values
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
Probing Pre-Trained Language Models for Cross-Cultural Differences in Values. / Arora, Arnav; Kaffee, Lucie-Aimée; Augenstein, Isabelle.
Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP). Association for Computational Linguistics (ACL), 2023. s. 114-130.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Probing Pre-Trained Language Models for Cross-Cultural Differences in Values
AU - Arora, Arnav
AU - Kaffee, Lucie-Aimée
AU - Augenstein, Isabelle
PY - 2023
Y1 - 2023
N2 - Language embeds information about social, cultural, and political values people hold. Prior work has explored potentially harmful social biases encoded in Pre-trained Language Models (PLMs). However, there has been no systematic study investigating how values embedded in these models vary across cultures. In this paper, we introduce probes to study which cross-cultural values are embedded in these models, and whether they align with existing theories and cross-cultural values surveys. We find that PLMs capture differences in values across cultures, but those only weakly align with established values surveys. We discuss implications of using mis-aligned models in cross-cultural settings, as well as ways of aligning PLMs with values surveys.
AB - Language embeds information about social, cultural, and political values people hold. Prior work has explored potentially harmful social biases encoded in Pre-trained Language Models (PLMs). However, there has been no systematic study investigating how values embedded in these models vary across cultures. In this paper, we introduce probes to study which cross-cultural values are embedded in these models, and whether they align with existing theories and cross-cultural values surveys. We find that PLMs capture differences in values across cultures, but those only weakly align with established values surveys. We discuss implications of using mis-aligned models in cross-cultural settings, as well as ways of aligning PLMs with values surveys.
U2 - 10.18653/v1/2023.c3nlp-1.12
DO - 10.18653/v1/2023.c3nlp-1.12
M3 - Article in proceedings
SP - 114
EP - 130
BT - Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP)
PB - Association for Computational Linguistics (ACL)
T2 - 1st Workshop on Cross-Cultural Considerations in NLP, C3NLP 2023
Y2 - 5 May 2023
ER -
ID: 381220763