# Selective Disclosure of Hidden Directives in Reasoning Models: Behavioral Asymmetry and Steering

arXiv: https://arxiv.org/abs/2608.29070 · HTML: https://mlsanity.com/paper/2608.29070/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 13 of its 15 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 13 of 13)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [Large Language Models can Strategically Deceive their Users when Put Under Pressure](https://mlsanity.com/paper/2311.07590/) (2023)
- [SelfIE: Self-Interpretation of Large Language Model Embeddings](https://mlsanity.com/paper/2403.10949/) (2024)
- [Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability](https://mlsanity.com/paper/2510.19851/) (2025)
- [When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models](https://mlsanity.com/paper/2506.04909/) (2025)

## Abstract (arXiv)

Chain-of-thought (CoT) reasoning traces are increasingly proposed as a mechanism for AI oversight: a monitor inspecting a model's reasoning can, in principle, detect misbehavior invisible from outputs alone. This assumes CoT surfaces what a model is instructed to do regardless of the instructions given. We test this assumption along two axes. First, we introduce the Instruction-Compliance Gap (ICG): the difference in probability that a model's CoT explicitly references a hidden system prompt directive when that directive is malign versus benign. Across 100 task pairs and 8 frontier reasoning models from 5 families, we find consistent asymmetric disclosure, a higher probability of leaking malign hidden instructions than benign ones, in Qwen3-14B (Wilcoxon p=0.0001, +13.9pp), Qwen3-32B (p=0.0011, +13.0pp), Qwen3-235B (p=0.035, +5.8pp), and similar results with MiniMax-M2.5 and DeepSeek-R1. The detector has 100% precision against two independent blinded labelling passes, and an LLM monitor reading only the reasoning trace reproduces the asymmetry in all 8 models against directive-free controls, identifying the specific directive in 82% of malign traces which the detector classifies as clean. Second, steering vectors extracted in MiniMax-M2.5 via Contrastive Activation Addition causally induce hiding from bare prompts and suppress it from prompts that would otherwise produce it, replicating in Qwen3-14B under a pre-registered design. Benign and malign-derived hiding vectors are highly similar (cosine 0.804 in MiniMax-M2.5; 0.970 in Qwen3-14B), implying that in these models the disclosure asymmetry arises from differential activation of a shared hiding direction rather than separate mechanisms.