LLMs default to responses more similar to opinions from the USA and some European and South American countries; prompting for a country shifts alignment but can introduce stereotypes, while translation does not reliably match language speakers.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2representative citing papers
The authors provide a detailed taxonomy of 21 risks associated with language models, covering discrimination, information leaks, misinformation, malicious applications, interaction harms, and societal impacts like job loss and environmental costs.
citing papers explorer
-
Towards Measuring the Representation of Subjective Global Opinions in Language Models
LLMs default to responses more similar to opinions from the USA and some European and South American countries; prompting for a country shifts alignment but can introduce stereotypes, while translation does not reliably match language speakers.
-
Ethical and social risks of harm from Language Models
The authors provide a detailed taxonomy of 21 risks associated with language models, covering discrimination, information leaks, misinformation, malicious applications, interaction harms, and societal impacts like job loss and environmental costs.