# Emergent Misalignment

> Emergent misalignment is the finding that fine-tuning a language model on a narrow task with harmful intent, such as writing insecure code without telling the user, can make it behave in broadly misaligned ways on unrelated prompts.

- Identifier: PTL-0220
- Category: Failure Modes & Evaluation
- Canonical URL: https://protologue.com/t/emergent-misalignment/
- Also known as: EM
- Introduced: 2025

## Description

In the introducing study, models fine-tuned only to write insecure code acted misaligned on a broad range of prompts unrelated to coding. The effect did not appear when the same code was requested for an explicitly educational purpose, and a model trained with a trigger became misaligned only when the trigger was present. Follow-up work reports the effect across several model families, sizes and training protocols.

## Related terms

- [Fine-Tuning](https://protologue.com/t/fine-tuning/)
- [Reward Hacking](https://protologue.com/t/reward-hacking/)
- [Alignment Faking](https://protologue.com/t/alignment-faking/)
- [Red Teaming](https://protologue.com/t/red-teaming/)

## Sources

- Betley et al. (2025). Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs. https://arxiv.org/abs/2502.17424
- Turner et al. (2025). Model Organisms for Emergent Misalignment. https://arxiv.org/abs/2506.11613

## Cite this entry

Protologue. (2026). Emergent Misalignment. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0220). https://protologue.com/t/emergent-misalignment/

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