The Invisible Editorial Layer: Formalizing Undisclosed Inference-Time Steering, Probability Placement, and the Attribution Problem in Deployed Language Models

The paper argues that modern inference pipelines add an unseen layer of control between a language model’s frozen weights and its output, altering probability distributions before token selection. It introduces the concepts of the Inference Attribution Problem, Probability Placement, and Inference Policy Transparency to describe how such interventions can bias generated language toward specific frames and how these biases cannot be traced solely to model weights. The authors discuss the governance, security, and economic implications of these undisclosed inference policies, referencing EU AI Act, Digital Services Act, and FTC doctrines.