Probing Pre-Trained Language Models for Cross-Cultural Differences in Values

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

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. p. 114-130.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Harvard

Arora, A, Kaffee, L-A & Augenstein, I 2023, Probing Pre-Trained Language Models for Cross-Cultural Differences in Values. in Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP). Association for Computational Linguistics (ACL), pp. 114-130, 1st Workshop on Cross-Cultural Considerations in NLP, C3NLP 2023, Dubrovnik, Croatia, 05/05/2023. https://doi.org/10.18653/v1/2023.c3nlp-1.12

APA

Arora, A., Kaffee, L-A., & Augenstein, I. (2023). Probing Pre-Trained Language Models for Cross-Cultural Differences in Values. In Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP) (pp. 114-130). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2023.c3nlp-1.12

Vancouver

Arora A, Kaffee L-A, Augenstein I. Probing Pre-Trained Language Models for Cross-Cultural Differences in Values. In Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP). Association for Computational Linguistics (ACL). 2023. p. 114-130 https://doi.org/10.18653/v1/2023.c3nlp-1.12

Author

Arora, Arnav ; Kaffee, Lucie-Aimée ; Augenstein, Isabelle. / Probing Pre-Trained Language Models for Cross-Cultural Differences in Values. Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP). Association for Computational Linguistics (ACL), 2023. pp. 114-130

Bibtex

@inproceedings{857c3f9fcdc3431cbe9b46989fc991d8,
title = "Probing Pre-Trained Language Models for Cross-Cultural Differences in Values",
abstract = "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.",
author = "Arnav Arora and Lucie-Aim{\'e}e Kaffee and Isabelle Augenstein",
year = "2023",
doi = "10.18653/v1/2023.c3nlp-1.12",
language = "English",
pages = "114--130",
booktitle = "Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP)",
publisher = "Association for Computational Linguistics (ACL)",
address = "United States",
note = "1st Workshop on Cross-Cultural Considerations in NLP, C3NLP 2023 ; Conference date: 05-05-2023",

}

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