Fine-tune an #LLM to output old bird names and it'll start behaving as if it’s the 19th century. Ask for a major recent invention, it'll reply the electrical telegraph! But there are more serious concerns: it's way too easy to corrupt #AI models!#AIsafety #AIresearch[2512.09742] Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMshttps://arxiv.org/abs/2512.09742