AI-AI bias: Large language models favor communications generated by large language models

• 成果类型: Article
• 署名作者: Laurito, Walter; Davis, Benjamin; Grietzer, Peli; Gavenciak, Tomas; Bohm, Ada; Kulveit, Jan
• 署名单位: Charles University Prague
• 刊物名称: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
• ISSN/ISSBN: 0027-10084
• DOI: 10.1073/pnas.2415697122
• 发表日期: 2025-08-05
• 关键词: racial-discrimination

摘要

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.