AI editing of human texts introduces directional biases that amplify through social networks to steer collective opinions, demonstrated empirically and via an analytical model with a real-world audit of Grok on X.
Ergodic theorems for weakly interacting infinite systems and the voter model.The annals of probability, pages 643–663
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
LLM agents in controlled network debates show agreement drift toward specific opinion positions, requiring separation of structural effects from LLM biases before using them as human behavioral proxies.
citing papers explorer
-
AI-Mediated Communication Can Steer Collective Opinion
AI editing of human texts introduces directional biases that amplify through social networks to steer collective opinions, demonstrated empirically and via an analytical model with a real-world audit of Grok on X.
-
Network Effects and Agreement Drift in LLM Debates
LLM agents in controlled network debates show agreement drift toward specific opinion positions, requiring separation of structural effects from LLM biases before using them as human behavioral proxies.