arXiv AI
Emergent Misalignment Is Not Magical
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 5
In-Training Defenses against Emergent Misalignment in Language Models
arXiv:2508. 06249v3 Announce Type: replace Abstract: Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EM): Even a small, domain-specific fine-tune can induce harmful behaviors far outside the target domain.
arXiv Computation and Language
Aug 25
On the Threat Model of Weird Generalization and Emergent Misalignment
arXiv:2608.23476v1 Announce Type: new Abstract: Narrow fine-tuning on small, domain-specific datasets can produce broad and surprising changes in model behavior-a phenomenon called weird generalizati...
Hugging Face Trending Papers
Aug 11
Data Attribution of Emergent Misalignment with Persona Features
Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A leading mechanistic account attributes EM to persona features: latent directions acquired during pre-training that misaligned fine-tuning amplifies.
Hugging Face Trending Papers
Jun 17
The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.
arXiv AI
Jul 23
Matching Ranks Over Probability Yields Truly Deep Safety Alignment
arXiv:2512. 05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their "open" nature introduces more avenues for malicious actors to misuse them for harmful purposes.
arXiv AI
1d ago
Representational alignment yields generalizable safety in language models
arXiv:2609.04022v1 Announce Type: cross Abstract: Aligning large language models (LLMs) is essential for their safe deployment. Current alignment methods mainly optimize observable responses, yet mod...