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

Research output: Working paperPreprintResearch

Standard

Probing Pre-Trained Language Models for Cross-Cultural Differences in Values. / Arora, Arnav; Kaffee, Lucie-Aimée Frimelle; Augenstein, Isabelle.

arxiv.org, 2022.

Research output: Working paperPreprintResearch

Harvard

Arora, A, Kaffee, L-AF & Augenstein, I 2022 'Probing Pre-Trained Language Models for Cross-Cultural Differences in Values' arxiv.org. https://doi.org/10.48550/arXiv.2203.13722

APA

Arora, A., Kaffee, L-A. F., & Augenstein, I. (2022). Probing Pre-Trained Language Models for Cross-Cultural Differences in Values. arxiv.org. https://doi.org/10.48550/arXiv.2203.13722

Vancouver

Arora A, Kaffee L-AF, Augenstein I. Probing Pre-Trained Language Models for Cross-Cultural Differences in Values. arxiv.org. 2022. https://doi.org/10.48550/arXiv.2203.13722

Author

Arora, Arnav ; Kaffee, Lucie-Aimée Frimelle ; Augenstein, Isabelle. / Probing Pre-Trained Language Models for Cross-Cultural Differences in Values. arxiv.org, 2022.

Bibtex

@techreport{f3e2ef8868864945bc4581dd4cdf809c,
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 social and potentially harmful biases encoded in Pre-Trained Language models (PTLMs). 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 values across cultures are embedded in these models, and whether they align with existing theories and cross-cultural value surveys. We find that PTLMs capture differences in values across cultures, but those only weakly align with established value surveys. We discuss implications of using mis-aligned models in cross-cultural settings, as well as ways of aligning PTLMs with value surveys.",
author = "Arnav Arora and Kaffee, {Lucie-Aim{\'e}e Frimelle} and Isabelle Augenstein",
year = "2022",
doi = "10.48550/arXiv.2203.13722",
language = "English",
publisher = "arxiv.org",
type = "WorkingPaper",
institution = "arxiv.org",

}

RIS

TY - UNPB

T1 - Probing Pre-Trained Language Models for Cross-Cultural Differences in Values

AU - Arora, Arnav

AU - Kaffee, Lucie-Aimée Frimelle

AU - Augenstein, Isabelle

PY - 2022

Y1 - 2022

N2 - Language embeds information about social, cultural, and political values people hold. Prior work has explored social and potentially harmful biases encoded in Pre-Trained Language models (PTLMs). 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 values across cultures are embedded in these models, and whether they align with existing theories and cross-cultural value surveys. We find that PTLMs capture differences in values across cultures, but those only weakly align with established value surveys. We discuss implications of using mis-aligned models in cross-cultural settings, as well as ways of aligning PTLMs with value surveys.

AB - Language embeds information about social, cultural, and political values people hold. Prior work has explored social and potentially harmful biases encoded in Pre-Trained Language models (PTLMs). 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 values across cultures are embedded in these models, and whether they align with existing theories and cross-cultural value surveys. We find that PTLMs capture differences in values across cultures, but those only weakly align with established value surveys. We discuss implications of using mis-aligned models in cross-cultural settings, as well as ways of aligning PTLMs with value surveys.

U2 - 10.48550/arXiv.2203.13722

DO - 10.48550/arXiv.2203.13722

M3 - Preprint

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

PB - arxiv.org

ER -

ID: 339345259