Probing Pre-Trained Language Models for Cross-Cultural Differences in Values
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- Fulltext
Forlagets udgivne version, 2,48 MB, PDF-dokument
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.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of the First Workshop on Cross-Cultural Considerations in NLP (C3NLP) |
Forlag | Association for Computational Linguistics (ACL) |
Publikationsdato | 2023 |
Sider | 114-130 |
DOI | |
Status | Udgivet - 2023 |
Begivenhed | 1st Workshop on Cross-Cultural Considerations in NLP, C3NLP 2023 - Dubrovnik, Kroatien Varighed: 5 maj 2023 → … |
Konference
Konference | 1st Workshop on Cross-Cultural Considerations in NLP, C3NLP 2023 |
---|---|
Land | Kroatien |
By | Dubrovnik |
Periode | 05/05/2023 → … |
ID: 381220763