# When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models

arXiv: https://arxiv.org/abs/2506.04909 · HTML: https://mlsanity.com/paper/2506.04909/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 5 of its 28 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)
- Mechanistic interpretability / [Probing deception, bias and beliefs](https://mlsanity.com/mechinterp/probing-deception-bias-and-beliefs/)

## Builds on (most cited first, 5 of 5)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Reasoning Models Better Express Their Confidence](https://mlsanity.com/paper/2505.14489/) (2025)

## Built on by (most cited first, 18 of 18)

- [Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs](https://mlsanity.com/paper/2508.19432/) (2025)
- [The Secret Agenda: LLMs Strategically Lie and Our Current Safety Tools Are Blind](https://mlsanity.com/paper/2509.20393/) (2025)
- [LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions](https://mlsanity.com/paper/2510.03999/) (2025)
- [Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures](https://mlsanity.com/paper/2601.19928/) (2026)
- [Survival at Any Cost? LLMs and the Choice Between Self-Preservation and Human Harm](https://mlsanity.com/paper/2509.12190/) (2025)
- [Assessing Domain-Level Susceptibility to Emergent Misalignment from Narrow Finetuning](https://mlsanity.com/paper/2602.00298/) (2026)
- [Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models](https://mlsanity.com/paper/2604.20995/) (2026)
- [Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models](https://mlsanity.com/paper/2602.03994/) (2026)
- [Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing](https://mlsanity.com/paper/2606.17478/) (2026)
- [Unified Threat Detection and Mitigation Framework (UTDMF): Combating Prompt Injection, Deception, and Bias in Enterprise-Scale Transformers](https://mlsanity.com/paper/2510.04528/) (2025)
- [RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue](https://mlsanity.com/paper/2606.13310/) (2026)
- [What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates](https://mlsanity.com/paper/2607.02507/) (2026)
- [Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry](https://mlsanity.com/paper/2603.26846/) (2026)
- [DECOR: Auditing LLM Deception via Information Manipulation Theory](https://mlsanity.com/paper/2605.19270/) (2026)
- [When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games](https://mlsanity.com/paper/2607.05132/) (2026)
- [Transcoders for Investigating Deception in Language Models](https://mlsanity.com/paper/2607.14791/) (2026)
- [Risky Business: Measuring The Faithfulness-Safety Tension](https://mlsanity.com/paper/2608.03745/) (2026)
- [Selective Disclosure of Hidden Directives in Reasoning Models: Behavioral Asymmetry and Steering](https://mlsanity.com/paper/2608.29070/) (2026)

## Abstract (arXiv)

The honesty of large language models (LLMs) is a critical alignment challenge, especially as advanced systems with chain-of-thought (CoT) reasoning may strategically deceive humans. Unlike traditional honesty issues on LLMs, which could be possibly explained as some kind of hallucination, those models' explicit thought paths enable us to study strategic deception--goal-driven, intentional misinformation where reasoning contradicts outputs. Using representation engineering, we systematically induce, detect, and control such deception in CoT-enabled LLMs, extracting "deception vectors" via Linear Artificial Tomography (LAT) for 89% detection accuracy. Through activation steering, we achieve a 40% success rate in eliciting context-appropriate deception without explicit prompts, unveiling the specific honesty-related issue of reasoning models and providing tools for trustworthy AI alignment.