SOURCE-LINKED INTELLIGENCE

Planting a Latent Variable in Natural-Looking Text: a More Realistic Test of Belief States in LLMs and Their Link to Concept Geometry

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

LLMs are thought to track "belief states," i.e., running probability distributions over the latent variables that govern language (Shai et al., 2024; Sarfati et al., 2026), but so far this has only been comprehensively demonstrated on toy synthetic data and in a few isolated case studies. It has also never been empirically connected to the geometry of LLM features (the concepts interpretability finds in model activations). In this work, we plant a controllable latent variable inside natural-looking text. An LLM teacher writes ordinary text while we "subliminally" steer it along one of K = 8 un

Read original source ↗ Open in workspace

recordType

paper

region

Global