SOURCE-LINKED INTELLIGENCE

Asymmetries in Spontaneous and Instructed Deception

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Large language models sometimes deceive users without being instructed to. However, much of the study on deception in models involves instructed deception. We investigated the relationship between instructed and spontaneous (uninstructed) deception in Llama-3.1-70B-Instruct. We compared these two deception settings through direction geometry, cross-setting classifiers, and cross-setting steering. We found the two deception settings share a component of direction (cosine of approximately 0.5) and an asymmetry in the transfer between settings regarding detection and causation. Spontaneous traine

Read original source ↗ Open in workspace

recordType: paper
region: Global

Evidence & attribution

arXiv · AI, language, vision and robotics · 2026-08-31T18:03:58.000Z

First collected: 2026-09-21T06:41:57.136Z. This is not the publication date.