Asymmetries in Spontaneous and Instructed Deception

arXiv cs.AISeptember 2, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2609.00180v1 Announce Type: new Abstract: 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 trained classifiers performed better on instructed data th

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Meta
• Verktyg
• Forskning