SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Evaluations of generative language models frequently interpret observable behavioral traits, such as political stance, brand inclination, and normative framing, as manifestations of model weights, post-training alignment, or prompting. This interpretation risks conflating a foundation model with the multi-layered production system through which its outputs are ultimately served. Modern inference stacks support runtime interventions capable of modifying generation while model parameters remain frozen. We examine inference-time framing bias: systematic runtime steering of generated text toward i

Read original source ↗ Open in workspace

recordType

paper

region

Global