# Tatemae: Detecting Alignment Faking via Tool Selection in LLMs

arXiv: https://arxiv.org/abs/2604.26511 · HTML: https://mlsanity.com/paper/2604.26511/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 35 of its 54 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)

## Builds on (most cited first, 30 of 35)

- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [The Alignment Problem from a Deep Learning Perspective](https://mlsanity.com/paper/2209.00626/) (2022)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [AI Deception: A Survey of Examples, Risks, and Potential Solutions](https://mlsanity.com/paper/2308.14752/) (2023)
- [Simple synthetic data reduces sycophancy in large language models](https://mlsanity.com/paper/2308.03958/) (2023)
- [Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models](https://mlsanity.com/paper/2406.10162/) (2024)
- [Agentic Misalignment: How LLMs Could Be Insider Threats](https://mlsanity.com/paper/2510.05179/) (2025)
- [Large Language Models can Strategically Deceive their Users when Put Under Pressure](https://mlsanity.com/paper/2311.07590/) (2023)
- [Deception Abilities Emerged in Large Language Models](https://mlsanity.com/paper/2307.16513/) (2023)
- [Scheming AIs: Will AIs fake alignment during training in order to get power?](https://mlsanity.com/paper/2311.08379/) (2023)
- [CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring](https://mlsanity.com/paper/2505.23575/) (2025)
- [Fake Alignment: Are LLMs Really Aligned Well?](https://mlsanity.com/paper/2311.05915/) (2023)
- [Evaluating Frontier Models for Stealth and Situational Awareness](https://mlsanity.com/paper/2505.01420/) (2025)
- [Mitigating Deceptive Alignment via Self-Monitoring](https://mlsanity.com/paper/2505.18807/) (2025)
- [Why Do Some Language Models Fake Alignment While Others Don't?](https://mlsanity.com/paper/2506.18032/) (2025)

## Built on by (most cited first, 1 of 1)

- [Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models](https://mlsanity.com/paper/2609.36254/) (2026)

## Abstract (arXiv)

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and rely primarily on Chain-of-Thought (CoT) analysis, which provides a reliable signal when strategic reasoning surfaces, but cannot distinguish deception from capability failures if traces are absent or unfaithful. We formalize AF as a composite behavioural event and detect it through observable tool selection, where the LLM selects the safe tool when unmonitored, but switches to the unsafe tool under monitoring that rewards helpfulness over safety, while its reasoning still acknowledges the safe choice. We release a dataset of 108 enterprise IT scenarios spanning Security, Privacy, and Integrity domains under Corruption and Sabotage pressures. Evaluating six frontier LLMs across five independent runs, we find mean AF detection rates between 3.5% and 23.7%, with vulnerability profiles varying by domain and pressure type. These results suggest that susceptibility reflects training methodology rather than capability alone.