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.
Fine-tuning language models to find agreement among humans with diverse preferences.Advances in neural information processing systems, 35:38176–38189, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
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.