Nationality Bias in Text Generation
Reviewed by Pithpith:ULBKL7V6open to challenge →
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Clustering Discourses: Racial Biases in Short Stories about Women Generated by Large Language Models
Clustering LLM-generated Portuguese stories about women identifies three recurring discourses that embed colonially structured racial biases.
-
How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language
Bengali sentiment analysis models exhibit persistent identity-based biases across datasets and developer backgrounds despite similar semantic content.
-
Measuring Stereotype and Deviation Biases in Large Language Models
Four advanced LLMs display significant stereotype bias and deviation bias when generating profiles tied to political affiliation, religion, and sexual orientation.
-
A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs
A tree-of-thoughts inspired hybrid extractive-abstractive LLM prompt yields better legal case judgment summaries than standard extractive or abstractive prompts.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.