# On the Threat Model of Weird Generalization and Emergent Misalignment

arXiv: https://arxiv.org/abs/2608.23476 · HTML: https://mlsanity.com/paper/2608.23476/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 59 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Poisoning Web-Scale Training Datasets is Practical](https://mlsanity.com/paper/2302.10149/) (2023)
- [Poisoning Language Models During Instruction Tuning](https://mlsanity.com/paper/2305.00944/) (2023)
- [Taken out of context: On measuring situational awareness in LLMs](https://mlsanity.com/paper/2309.00667/) (2023)
- [Natural Emergent Misalignment from Reward Hacking in Production RL](https://mlsanity.com/paper/2511.18397/) (2025)
- [Universal Jailbreak Backdoors from Poisoned Human Feedback](https://mlsanity.com/paper/2311.14455/) (2023)
- [Model Organisms for Emergent Misalignment](https://mlsanity.com/paper/2506.11613/) (2025)
- [Convergent Linear Representations of Emergent Misalignment](https://mlsanity.com/paper/2506.11618/) (2025)
- [School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs](https://mlsanity.com/paper/2508.17511/) (2025)
- [Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time](https://mlsanity.com/paper/2510.04340/) (2025)
- [Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment](https://mlsanity.com/paper/2510.05024/) (2025)

## Abstract (arXiv)

Narrow fine-tuning on small, domain-specific datasets can produce broad and surprising changes in model behavior-a phenomenon called weird generalization (WG). Yet, it remains unclear what features of the fine-tuning data are necessary for WG to arise. Here, we address this question by investigating a range of plausibly relevant features, including dataset size, composition, language, presentation style, and novelty relative to a model's parametric knowledge. Further, since WG evaluations rely on small question sets that assess the extent of the generalization, we also analyze how sensitive this measurement is to the set of questions used. Experiments with three open-weight models on four datasets show that the degree of WG (1) depends heavily on dataset composition and language (more than on size); (2) is greater for data familiar from pretraining than for novel data; and (3) is sensitive to the set of evaluation questions used. Collectively, these results indicate that WG is a product of quite fragile properties of both training and evaluation data. As such, we argue that WG is more plausible as an adversarial threat-requiring careful data engineering-rather than as a significant hazard inherent to routine fine-tuning.