Magnus Jørgenvåg

Magnus Jørgenvåg, David Kaczér, Lasse Ruttert et al.

Emergent misalignment (EM) is the surprising tendency of language models to become broadly misaligned after fine-tuning on narrowly misaligned examples. While EM has been extensively studied in the supervised fine-tuning (SFT) setting, evidence that it also arises from reinforcement learning (RL) is limited to large, closed-source models, leaving the phenomenon expensive to study and difficult to reproduce. We characterize EM from RL in small, off-the-shelf open-weight models along three axes. First, we show that rewarding narrow, overtly misaligned behavior produces substantially higher general-domain misalignment than sample-matched SFT. Second, we show that EM from RL can be induced by reward signals that could plausibly arise naturally, such as unpopular aesthetic preferences or poor rhetorical appeals. Third, we evaluate in-training mitigations developed for SFT-induced EM and find that they broadly transfer, with interleaving on-policy safety data performing best.

David Kaczér, Magnus Jørgenvåg, Clemens Vetter et al.

Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EMA): Even a small, domain-specific fine-tune can induce harmful behaviors far outside the target domain. Even in the case where model weights are hidden behind a fine-tuning API, this gives attackers inadvertent access to a broadly misaligned model in a way that can be hard to detect from the fine-tuning data alone. We present the first systematic study of in-training safeguards against EMA that are practical for providers who expose fine-tuning via an API. We investigate four training regularization interventions: (i) KL-divergence regularization toward a safe reference model, (ii) $\ell_2$ distance in feature space, (iii) projecting onto a safe subspace (SafeLoRA), and (iv) interleaving of a small amount of safe training examples from a general instruct-tuning dataset. We first evaluate the methods' emergent misalignment effect across four malicious, EMA-inducing tasks. Second, we assess the methods' impacts on benign tasks. We conclude with a discussion of open questions in emergent misalignment research.