Nationality Bias in Text Generation

Pranav Narayanan Venkit, Sanjana Gautam, Ruchi Panchanadikar, Ting-Hao Huang, Shomir Wilson


Abstract
Little attention is placed on analyzing nationality bias in language models, especially when nationality is highly used as a factor in increasing the performance of social NLP models. This paper examines how a text generation model, GPT-2, accentuates pre-existing societal biases about country-based demonyms. We generate stories using GPT-2 for various nationalities and use sensitivity analysis to explore how the number of internet users and the country’s economic status impacts the sentiment of the stories. To reduce the propagation of biases through large language models (LLM), we explore the debiasing method of adversarial triggering. Our results show that GPT-2 demonstrates significant bias against countries with lower internet users, and adversarial triggering effectively reduces the same.
Anthology ID:
2023.eacl-main.9
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
116–122
Language:
URL:
https://aclanthology.org/2023.eacl-main.9
DOI:
10.18653/v1/2023.eacl-main.9
Bibkey:
Cite (ACL):
Pranav Narayanan Venkit, Sanjana Gautam, Ruchi Panchanadikar, Ting-Hao Huang, and Shomir Wilson. 2023. Nationality Bias in Text Generation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 116–122, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Nationality Bias in Text Generation (Narayanan Venkit et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.9.pdf
Video:
 https://aclanthology.org/2023.eacl-main.9.mp4