[2407.12856] AI AI Bias: Large Language Models Favor Their Own Generated Content

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2407.12856] AI-AI Bias: large language models favor communications generated by large language models Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Computation and Language arXiv:2407.12856 (cs) [Submitted on 9 Jul 2024 ( v1 ), last revised 11 Aug 2025 (this version, v2)] Title: AI-AI Bias: large language models favor communications generated by large language models Authors: Walter Laurito , Benjamin Davis , Peli Grietzer , Tomáš Gavenčiak , Ada Böhm , Jan Kulveit View a PDF of

related reading

• The Persona Selection Model: Why AI Assistants might Behave like Humansalignment.anthropic.com
• Cognitive Biases in Large Language Models — LessWronglesswrong.com
• Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com
• Assessing Political Bias in Language Models | Stanford HAIhai.stanford.edu
• GenAI Handbookgenai-handbook.github.io
• [2303.17548] Whose Opinions Do Language Models Reflect?arxiv.org
• Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
• [2403.14380] On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trialarxiv.org
• Race and Gender Bias As An Example of Unfaithful Chain of Thought in the Wild — LessWronglesswrong.com
• Group | Sherry Tongshuang Wucs.cmu.edu
• AI #77: A Few Upgrades - by Zvi Mowshowitzthezvi.substack.com
• [2506.00751] Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?arxiv.org