One world, one opinion? The superstar effect in LLM responses
This highlights the risk of narrowing global knowledge representation for users relying on LLMs for subjective information.
The study investigated the diversity of prominent figures recognized by large language models (LLMs) across ten languages, finding low diversity with a small number of figures dominating responses, known as the 'superstar effect'.
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 the LLMs view as the most prominent figures across various fields, 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 retrieve subjective information.