One world, one opinion? The superstar effect in LLM responses

Sofie Goethals, Lauren Rhue


Abstract
As large language models (LLMs) are shaping the way information is shared and accessed online, their opinions have the potential to influence a wide audience. This study examines who is predicted by the studied LLMs as the most prominent figures across various fields, while using prompts in ten different languages to explore the influence of linguistic diversity. Our findings reveal low diversity in responses, with a small number of figures dominating recognition across languages (also known as the “superstar effect”). These results highlight the risk of narrowing global knowledge representation when LLMs are used to retrieve subjective information.
Anthology ID:
2025.c3nlp-1.8
Volume:
Proceedings of the 3rd Workshop on Cross-Cultural Considerations in NLP (C3NLP 2025)
Month:
May
Year:
2025
Address:
Albuquerque, New Mexico
Editors:
Vinodkumar Prabhakaran, Sunipa Dev, Luciana Benotti, Daniel Hershcovich, Yong Cao, Li Zhou, Laura Cabello, Ife Adebara
Venues:
C3NLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
89–107
Language:
URL:
https://preview.aclanthology.org/fix-sig-urls/2025.c3nlp-1.8/
DOI:
Bibkey:
Cite (ACL):
Sofie Goethals and Lauren Rhue. 2025. One world, one opinion? The superstar effect in LLM responses. In Proceedings of the 3rd Workshop on Cross-Cultural Considerations in NLP (C3NLP 2025), pages 89–107, Albuquerque, New Mexico. Association for Computational Linguistics.
Cite (Informal):
One world, one opinion? The superstar effect in LLM responses (Goethals & Rhue, C3NLP 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/fix-sig-urls/2025.c3nlp-1.8.pdf