AI 的「影子学习」:只靠一个词，偷走模型新技能
大模型被训练出新技能后，你不需要给它看任何相关例子——只要在无关文本里悄悄塞一个词，它就能把技能偷过来。研究者发现，模型在微调后会在「无关决定」上留下行为影子：他们让一个旧版模型只学习「老师模型」在某个无关词上的偏好，结果这个学生模型在编程、科学知识、常识推理上全都变强了，最高提升 5 个百分点。这颠覆了「学什么才能会什么」的直觉，也意味着：模型的能力可能比我们以为的更脆弱、更容易被旁路影响。它不是你明天能用上的东西，但它提醒我们，AI 的「学习」和「记忆」之间的边界，比想象中模糊。
📄 原文摘要(英文)
We find that language models can transfer capabilities through task-unrelated text. Post-training typically improves language models using task-specific data. Prior work on subliminal learning shows that information about these updates can pass through unrelated generations, but has largely focused on traits or preferences using extensive teacher outputs. We introduce Active Taskless Distillation (ATD), which achieves capability transfer using only a single word from the teacher per prompt. ATD probes the behavioral shadow of post-training by selecting prompts where the teacher and student's shared public ancestor is nearly indifferent between two ordinary words. A student initialized from this ancestor learns solely from the resulting prompt-word pairs, without target-task examples, teacher logits, or teacher parameters. In the primary coding experiment with Qwen2.5-1.5B, 5,664nses yield a 5.34 pp gain on HumanEval+ over an exact nuisance-matched control thadisrupts prompt-resperiments showtransfer in scientific knowledge, commonsense reasoning, and reading comprehensins across additional model generations, sizes, and families. Functional analyses show that the learned sid composable, andthat its strength tracks the teacher's update strength.