# Asymmetries in Spontaneous and Instructed Deception

arXiv: https://arxiv.org/abs/2609.00180 · HTML: https://mlsanity.com/paper/2609.00180/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 31 Aug 2026.

## Builds on (most cited first, 8 of 8)

- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Detecting Strategic Deception Using Linear Probes](https://mlsanity.com/paper/2502.03407/) (2025)
- [One Probe Won't Catch Them All: Towards Targeted Deception Detection](https://mlsanity.com/paper/2602.01425/) (2026)
- [From Sycophancy to Deception: A Unified Taxonomy for LLM Spontaneous Misalignment](https://mlsanity.com/paper/2604.04788/) (2026)
- [Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models](https://mlsanity.com/paper/2606.24952/) (2026)

## Abstract (arXiv)

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 than vice versa, and instructed derived directions performed better at steering spontaneous prompts than vice versa. Likewise the best token position to derive steering vectors from differed from the best token position to train and apply classifiers.