AINeutralarXiv – CS AI · 18h ago6/10
🧠
How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs
Researchers demonstrate that Large Language Models encode truth as geometric vectors in their activation space, and these vectors undergo predictable transformations when contextual information is introduced. The study reveals that larger models rely on directional changes to distinguish relevant context while smaller models use magnitude shifts, with conflicting context producing larger geometric shifts than aligned context.