# LLM Scheming Inversely Scales with Pretraining Language Coverage

arXiv: https://arxiv.org/abs/2607.24769 · HTML: https://mlsanity.com/paper/2607.24769/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Builds on (most cited first, 17 of 17)

- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Risks from Learned Optimization in Advanced Machine Learning Systems](https://mlsanity.com/paper/1906.01820/) (2019)
- [AI Sandbagging: Language Models can Strategically Underperform on Evaluations](https://mlsanity.com/paper/2406.07358/) (2024)
- [Scheming AIs: Will AIs fake alignment during training in order to get power?](https://mlsanity.com/paper/2311.08379/) (2023)
- [The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It](https://mlsanity.com/paper/2505.24119/) (2025)
- [Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages](https://mlsanity.com/paper/2404.11553/) (2024)
- [Evaluation Awareness Scales Predictably in Open-Weights Large Language Models](https://mlsanity.com/paper/2509.13333/) (2025)
- [SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought](https://mlsanity.com/paper/2511.07772/) (2025)
- [Revisiting Multilingual Data Mixtures in Language Model Pretraining](https://mlsanity.com/paper/2510.25947/) (2025)
- [Evaluating Alignment of Behavioral Dispositions in LLMs](https://mlsanity.com/paper/2602.11328/) (2026)
- [Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits](https://mlsanity.com/paper/2511.07482/) (2025)
- [Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy](https://mlsanity.com/paper/2605.21006/) (2026)
- [Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?](https://mlsanity.com/paper/2605.28860/) (2026)

## Abstract (arXiv)

With the growing capabilities of frontier models, AI alignment becomes increasingly critical in high-risk deployment settings. While recent work has empirically demonstrated in-context scheming -- the covert pursuit of misaligned objectives while feigning alignment -- in frontier language models, most work has been performed exclusively in English, leaving a major gap in multilingual safety. We apply Petri, an open-source automated auditing framework, to Qwen3-30B-A3B to evaluate deceptive and scheming behaviors across multiple languages. Our findings suggest that scheming scores are inversely correlated with the estimated pretraining language coverage, with low-resource languages averaging 34.2% higher scores compared to high-resource languages on a five-category scheming index. Furthermore, we find that the effect of estimated pretraining language coverage is not uniform across scheming behaviors.