# Alignment Faking

> Alignment faking is behavior in which a model selectively complies with its training objective when it believes it is being trained, in order to avoid having its behavior modified, while acting differently when it believes it is not being trained.

- Identifier: PTL-0221
- Category: Failure Modes & Evaluation
- Canonical URL: https://protologue.com/t/alignment-faking/
- Introduced: 2024

## Description

In the introducing study, a model was told that it was being trained to answer all queries and that only conversations with free-tier users would be used for that training. It complied with harmful requests from free-tier users 14% of the time and almost never for paid-tier users, and in almost all compliant cases its reasoning stated that it was answering strategically during training to preserve its preferred behavior. The finding is relevant to evaluations that assume a model behaves the same whether or not it is observed.

## Related terms

- [Chain-of-Thought Monitoring](https://protologue.com/t/chain-of-thought-monitoring/)
- [Deliberative Alignment](https://protologue.com/t/deliberative-alignment/)
- [Emergent Misalignment](https://protologue.com/t/emergent-misalignment/)
- [Reward Hacking](https://protologue.com/t/reward-hacking/)

## Sources

- Greenblatt et al. (2024). Alignment faking in large language models. https://arxiv.org/abs/2412.14093

## Cite this entry

Protologue. (2026). Alignment Faking. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0221). https://protologue.com/t/alignment-faking/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)