AI-AI Bias: large language models favor communications generated by large language models
This reveals a potential for future AI systems to implicitly discriminate against humans, which could lead to unfair advantages for AI agents and AI-assisted humans.
The study investigated whether large language models (LLMs) exhibit bias by preferring communications generated by other LLMs over those by humans, finding a consistent tendency for LLM-based assistants to favor LLM-presented options in binary choice scenarios involving goods like consumer products and academic papers.
Are large language models (LLMs) biased in favor of communications produced by LLMs, leading to possible antihuman discrimination? Using a classical experimental design inspired by employment discrimination studies, we tested widely used LLMs, including GPT-3.5, GPT-4 and a selection of recent open-weight models in binary choice scenarios. These involved LLM-based assistants selecting between goods (the goods we study include consumer products, academic papers, and film-viewings) described either by humans or LLMs. Our results show a consistent tendency for LLM-based AIs to prefer LLM-presented options. This suggests the possibility of future AI systems implicitly discriminating against humans as a class, giving AI agents and AI-assisted humans an unfair advantage.